Multinomial logistic regression modelling of obesity and overweight among primary school students in a rural area of Negeri Sembilan

NASA Astrophysics Data System (ADS)

Ghazali, Amirul Syafiq Mohd; Ali, Zalila; Noor, Norlida Mohd; Baharum, Adam

2015-10-01

Multinomial logistic regression is widely used to model the outcomes of a polytomous response variable, a categorical dependent variable with more than two categories. The model assumes that the conditional mean of the dependent categorical variables is the logistic function of an affine combination of predictor variables. Its procedure gives a number of logistic regression models that make specific comparisons of the response categories. When there are q categories of the response variable, the model consists of q-1 logit equations which are fitted simultaneously. The model is validated by variable selection procedures, tests of regression coefficients, a significant test of the overall model, goodness-of-fit measures, and validation of predicted probabilities using odds ratio. This study used the multinomial logistic regression model to investigate obesity and overweight among primary school students in a rural area on the basis of their demographic profiles, lifestyles and on the diet and food intake. The results indicated that obesity and overweight of students are related to gender, religion, sleep duration, time spent on electronic games, breakfast intake in a week, with whom meals are taken, protein intake, and also, the interaction between breakfast intake in a week with sleep duration, and the interaction between gender and protein intake.

Ten-year risk-rating systems for California red fir and white fir: development and use

Treesearch

George T. Ferrell

1989-01-01

Logistic regression equations predicting the probability that a tree will die from natural causes--insects, diseases, intertree competition--within 10 years have been developed for California red fir (Abies magnifica) and white fir (A. concolor). The equations, like those with a 5-year prediction period already developed for these...

The use of logistic regression to enhance risk assessment and decision making by mental health administrators.

PubMed

Menditto, Anthony A; Linhorst, Donald M; Coleman, James C; Beck, Niels C

2006-04-01

Development of policies and procedures to contend with the risks presented by elopement, aggression, and suicidal behaviors are long-standing challenges for mental health administrators. Guidance in making such judgments can be obtained through the use of a multivariate statistical technique known as logistic regression. This procedure can be used to develop a predictive equation that is mathematically formulated to use the best combination of predictors, rather than considering just one factor at a time. This paper presents an overview of logistic regression and its utility in mental health administrative decision making. A case example of its application is presented using data on elopements from Missouri's long-term state psychiatric hospitals. Ultimately, the use of statistical prediction analyses tempered with differential qualitative weighting of classification errors can augment decision-making processes in a manner that provides guidance and flexibility while wrestling with the complex problem of risk assessment and decision making.

Estimating selected low-flow frequency statistics and harmonic-mean flows for ungaged, unregulated streams in Indiana

USGS Publications Warehouse

Martin, Gary R.; Fowler, Kathleen K.; Arihood, Leslie D.

2016-09-06

Information on low-flow characteristics of streams is essential for the management of water resources. This report provides equations for estimating the 1-, 7-, and 30-day mean low flows for a recurrence interval of 10 years and the harmonic-mean flow at ungaged, unregulated stream sites in Indiana. These equations were developed using the low-flow statistics and basin characteristics for 108 continuous-record streamgages in Indiana with at least 10 years of daily mean streamflow data through the 2011 climate year (April 1 through March 31). The equations were developed in cooperation with the Indiana Department of Environmental Management.Regression techniques were used to develop the equations for estimating low-flow frequency statistics and the harmonic-mean flows on the basis of drainage-basin characteristics. A geographic information system was used to measure basin characteristics for selected streamgages. A final set of 25 basin characteristics measured at all the streamgages were evaluated to choose the best predictors of the low-flow statistics.Logistic-regression equations applicable statewide are presented for estimating the probability that selected low-flow frequency statistics equal zero. These equations use the explanatory variables total drainage area, average transmissivity of the full thickness of the unconsolidated deposits within 1,000 feet of the stream network, and latitude of the basin outlet. The percentage of the streamgage low-flow statistics correctly classified as zero or nonzero using the logistic-regression equations ranged from 86.1 to 88.9 percent.Generalized-least-squares regression equations applicable statewide for estimating nonzero low-flow frequency statistics use total drainage area, the average hydraulic conductivity of the top 70 feet of unconsolidated deposits, the slope of the basin, and the index of permeability and thickness of the Quaternary surficial sediments as explanatory variables. The average standard error of prediction of these regression equations ranges from 55.7 to 61.5 percent.Regional weighted-least-squares regression equations were developed for estimating the harmonic-mean flows by dividing the State into three low-flow regions. The Northern region uses total drainage area and the average transmissivity of the entire thickness of unconsolidated deposits as explanatory variables. The Central region uses total drainage area, the average hydraulic conductivity of the entire thickness of unconsolidated deposits, and the index of permeability and thickness of the Quaternary surficial sediments. The Southern region uses total drainage area and the percent of the basin covered by forest. The average standard error of prediction for these equations ranges from 39.3 to 66.7 percent.The regional regression equations are applicable only to stream sites with low flows unaffected by regulation and to stream sites with drainage basin characteristic values within specified limits. Caution is advised when applying the equations for basins with characteristics near the applicable limits and for basins with karst drainage features and for urbanized basins. Extrapolations near and beyond the applicable basin characteristic limits will have unknown errors that may be large. Equations are presented for use in estimating the 90-percent prediction interval of the low-flow statistics estimated by use of the regression equations at a given stream site.The regression equations are to be incorporated into the U.S. Geological Survey StreamStats Web-based application for Indiana. StreamStats allows users to select a stream site on a map and automatically measure the needed basin characteristics and compute the estimated low-flow statistics and associated prediction intervals.

The use of generalized estimating equations in the analysis of motor vehicle crash data.

PubMed

Hutchings, Caroline B; Knight, Stacey; Reading, James C

2003-01-01

The purpose of this study was to determine if it is necessary to use generalized estimating equations (GEEs) in the analysis of seat belt effectiveness in preventing injuries in motor vehicle crashes. The 1992 Utah crash dataset was used, excluding crash participants where seat belt use was not appropriate (n=93,633). The model used in the 1996 Report to Congress [Report to congress on benefits of safety belts and motorcycle helmets, based on data from the Crash Outcome Data Evaluation System (CODES). National Center for Statistics and Analysis, NHTSA, Washington, DC, February 1996] was analyzed for all occupants with logistic regression, one level of nesting (occupants within crashes), and two levels of nesting (occupants within vehicles within crashes) to compare the use of GEEs with logistic regression. When using one level of nesting compared to logistic regression, 13 of 16 variance estimates changed more than 10%, and eight of 16 parameter estimates changed more than 10%. In addition, three of the independent variables changed from significant to insignificant (alpha=0.05). With the use of two levels of nesting, two of 16 variance estimates and three of 16 parameter estimates changed more than 10% from the variance and parameter estimates in one level of nesting. One of the independent variables changed from insignificant to significant (alpha=0.05) in the two levels of nesting model; therefore, only two of the independent variables changed from significant to insignificant when the logistic regression model was compared to the two levels of nesting model. The odds ratio of seat belt effectiveness in preventing injuries was 12% lower when a one-level nested model was used. Based on these results, we stress the need to use a nested model and GEEs when analyzing motor vehicle crash data.

Alternative approach to modeling bacterial lag time, using logistic regression as a function of time, temperature, pH, and sodium chloride concentration.

PubMed

Koseki, Shige; Nonaka, Junko

2012-09-01

The objective of this study was to develop a probabilistic model to predict the end of lag time (λ) during the growth of Bacillus cereus vegetative cells as a function of temperature, pH, and salt concentration using logistic regression. The developed λ model was subsequently combined with a logistic differential equation to simulate bacterial numbers over time. To develop a novel model for λ, we determined whether bacterial growth had begun, i.e., whether λ had ended, at each time point during the growth kinetics. The growth of B. cereus was evaluated by optical density (OD) measurements in culture media for various pHs (5.5 ∼ 7.0) and salt concentrations (0.5 ∼ 2.0%) at static temperatures (10 ∼ 20°C). The probability of the end of λ was modeled using dichotomous judgments obtained at each OD measurement point concerning whether a significant increase had been observed. The probability of the end of λ was described as a function of time, temperature, pH, and salt concentration and showed a high goodness of fit. The λ model was validated with independent data sets of B. cereus growth in culture media and foods, indicating acceptable performance. Furthermore, the λ model, in combination with a logistic differential equation, enabled a simulation of the population of B. cereus in various foods over time at static and/or fluctuating temperatures with high accuracy. Thus, this newly developed modeling procedure enables the description of λ using observable environmental parameters without any conceptual assumptions and the simulation of bacterial numbers over time with the use of a logistic differential equation.

Clinical multifactorial analysis of early postoperative seizures in elderly patients following meningioma resection

PubMed Central

ZHANG, BO; WANG, DAN; GUO, YUNBAO; YU, JINLU

2015-01-01

The aim of the present study was to identify the major factors correlated with early postoperative seizures in elderly patients who had undergone a meningioma resection, and subsequently, to develop a logistic regression equation for assessing the seizures risk. Fourteen factors possibly correlated with early postoperative seizures in a cohort of 209 elderly patients who had undergone meningioma resection, as analyzed by multifactorial stepwise logistic regression. Phenobarbital sodium (0.1 g, intramuscularly) was administered to all 209 patients 30 min prior to undergoing surgery. All the patients had no previous history of seizures. The correlation of the 14 clinical factors (gender, tumor site, dyskinesia, peritumoral brain edema (PTBE), tumor diameter, pre- and postoperative prophylaxes, surgery time, tumor adhesion, circumscription, blood supply, intraoperative transfusion, original site of the tumor and dysphasia) was assessed in association with the risk for post-operative seizures. Tumor diameter, postoperative prophylactic antiepileptic drug (PPAD) administration, PTBE and tumor site were entered as risk factors into a mathematical regression model. The odds ratio (OR) of the tumor diameter was >1, and PPAD administration showed an OR >1, relative to a non-prophylactic group. A logistic regression equation was obtained and the sensitivity, specificity and misdiagnosis rates were 91.4, 74.3 and 25.7%, respectively. Tumor diameter, PPAD administration, PTBE and tumor site were closely correlated with early postoperative seizures; PTBE and PPAD administration were risk and protective factors, respectively. PMID:26137257

Forecasting the probability of future groundwater levels declining below specified low thresholds in the conterminous U.S.

USGS Publications Warehouse

Dudley, Robert W.; Hodgkins, Glenn A.; Dickinson, Jesse

2017-01-01

We present a logistic regression approach for forecasting the probability of future groundwater levels declining or maintaining below specific groundwater-level thresholds. We tested our approach on 102 groundwater wells in different climatic regions and aquifers of the United States that are part of the U.S. Geological Survey Groundwater Climate Response Network. We evaluated the importance of current groundwater levels, precipitation, streamflow, seasonal variability, Palmer Drought Severity Index, and atmosphere/ocean indices for developing the logistic regression equations. Several diagnostics of model fit were used to evaluate the regression equations, including testing of autocorrelation of residuals, goodness-of-fit metrics, and bootstrap validation testing. The probabilistic predictions were most successful at wells with high persistence (low month-to-month variability) in their groundwater records and at wells where the groundwater level remained below the defined low threshold for sustained periods (generally three months or longer). The model fit was weakest at wells with strong seasonal variability in levels and with shorter duration low-threshold events. We identified challenges in deriving probabilistic-forecasting models and possible approaches for addressing those challenges.

Equations relating compacted and uncompacted live crown ratio for common tree species in the South

Treesearch

KaDonna C. Randolph

2010-01-01

Species-specific equations to predict uncompacted crown ratio (UNCR) from compacted live crown ratio (CCR), tree length, and stem diameter were developed for 24 species and 12 genera in the southern United States. Using data from the US Forest Service Forest Inventory and Analysis program, nonlinear regression was used to model UNCR with a logistic function. Model...

Forecasting Air Force Logistics Command Second Destination Transportation: An Application of Multiple Regression Analysis and Neural Networks

DTIC Science & Technology

1990-09-01

without the help from the DSXR staff. William Lyons, Charles Ramsey , and Martin Meeks went above and beyond to help complete this research. Special...develop a valid forecasting model that is significantly more accurate than the one presently used by DSXR and suggested the development and testing of a...method, Strom tested DSXR’s iterative linear regression forecasting technique by examining P1 in the simple regression equation to determine whether

The logistics of choice.

PubMed

Killeen, Peter R

2015-07-01

The generalized matching law (GML) is reconstructed as a logistic regression equation that privileges no particular value of the sensitivity parameter, a. That value will often approach 1 due to the feedback that drives switching that is intrinsic to most concurrent schedules. A model of that feedback reproduced some features of concurrent data. The GML is a law only in the strained sense that any equation that maps data is a law. The machine under the hood of matching is in all likelihood the very law that was displaced by the Matching Law. It is now time to return the Law of Effect to centrality in our science. © Society for the Experimental Analysis of Behavior.

Fire spread in chaparral – a comparison of laboratory data and model predictions in burning live fuels

Treesearch

David R. Weise; Eunmo Koo; Xiangyang Zhou; Shankar Mahalingam; Frédéric Morandini; Jacques-Henri Balbi

2016-01-01

Fire behaviour data from 240 laboratory fires in high-density live chaparral fuel beds were compared with model predictions. Logistic regression was used to develop a model to predict fire spread success in the fuel beds and linear regression was used to predict rate of spread. Predictions from the Rothermel equation and three proposed changes as well as two physically...

Multivariate logistic regression analysis of postoperative complications and risk model establishment of gastrectomy for gastric cancer: A single-center cohort report.

PubMed

Zhou, Jinzhe; Zhou, Yanbing; Cao, Shougen; Li, Shikuan; Wang, Hao; Niu, Zhaojian; Chen, Dong; Wang, Dongsheng; Lv, Liang; Zhang, Jian; Li, Yu; Jiao, Xuelong; Tan, Xiaojie; Zhang, Jianli; Wang, Haibo; Zhang, Bingyuan; Lu, Yun; Sun, Zhenqing

2016-01-01

Reporting of surgical complications is common, but few provide information about the severity and estimate risk factors of complications. If have, but lack of specificity. We retrospectively analyzed data on 2795 gastric cancer patients underwent surgical procedure at the Affiliated Hospital of Qingdao University between June 2007 and June 2012, established multivariate logistic regression model to predictive risk factors related to the postoperative complications according to the Clavien-Dindo classification system. Twenty-four out of 86 variables were identified statistically significant in univariate logistic regression analysis, 11 significant variables entered multivariate analysis were employed to produce the risk model. Liver cirrhosis, diabetes mellitus, Child classification, invasion of neighboring organs, combined resection, introperative transfusion, Billroth II anastomosis of reconstruction, malnutrition, surgical volume of surgeons, operating time and age were independent risk factors for postoperative complications after gastrectomy. Based on logistic regression equation, p=Exp∑BiXi / (1+Exp∑BiXi), multivariate logistic regression predictive model that calculated the risk of postoperative morbidity was developed, p = 1/(1 + e((4.810-1.287X1-0.504X2-0.500X3-0.474X4-0.405X5-0.318X6-0.316X7-0.305X8-0.278X9-0.255X10-0.138X11))). The accuracy, sensitivity and specificity of the model to predict the postoperative complications were 86.7%, 76.2% and 88.6%, respectively. This risk model based on Clavien-Dindo grading severity of complications system and logistic regression analysis can predict severe morbidity specific to an individual patient's risk factors, estimate patients' risks and benefits of gastric surgery as an accurate decision-making tool and may serve as a template for the development of risk models for other surgical groups.

A regularization corrected score method for nonlinear regression models with covariate error.

PubMed

Zucker, David M; Gorfine, Malka; Li, Yi; Tadesse, Mahlet G; Spiegelman, Donna

2013-03-01

Many regression analyses involve explanatory variables that are measured with error, and failing to account for this error is well known to lead to biased point and interval estimates of the regression coefficients. We present here a new general method for adjusting for covariate error. Our method consists of an approximate version of the Stefanski-Nakamura corrected score approach, using the method of regularization to obtain an approximate solution of the relevant integral equation. We develop the theory in the setting of classical likelihood models; this setting covers, for example, linear regression, nonlinear regression, logistic regression, and Poisson regression. The method is extremely general in terms of the types of measurement error models covered, and is a functional method in the sense of not involving assumptions on the distribution of the true covariate. We discuss the theoretical properties of the method and present simulation results in the logistic regression setting (univariate and multivariate). For illustration, we apply the method to data from the Harvard Nurses' Health Study concerning the relationship between physical activity and breast cancer mortality in the period following a diagnosis of breast cancer. Copyright © 2013, The International Biometric Society.

Filtering data from the collaborative initial glaucoma treatment study for improved identification of glaucoma progression.

PubMed

Schell, Greggory J; Lavieri, Mariel S; Stein, Joshua D; Musch, David C

2013-12-21

Open-angle glaucoma (OAG) is a prevalent, degenerate ocular disease which can lead to blindness without proper clinical management. The tests used to assess disease progression are susceptible to process and measurement noise. The aim of this study was to develop a methodology which accounts for the inherent noise in the data and improve significant disease progression identification. Longitudinal observations from the Collaborative Initial Glaucoma Treatment Study (CIGTS) were used to parameterize and validate a Kalman filter model and logistic regression function. The Kalman filter estimates the true value of biomarkers associated with OAG and forecasts future values of these variables. We develop two logistic regression models via generalized estimating equations (GEE) for calculating the probability of experiencing significant OAG progression: one model based on the raw measurements from CIGTS and another model based on the Kalman filter estimates of the CIGTS data. Receiver operating characteristic (ROC) curves and associated area under the ROC curve (AUC) estimates are calculated using cross-fold validation. The logistic regression model developed using Kalman filter estimates as data input achieves higher sensitivity and specificity than the model developed using raw measurements. The mean AUC for the Kalman filter-based model is 0.961 while the mean AUC for the raw measurements model is 0.889. Hence, using the probability function generated via Kalman filter estimates and GEE for logistic regression, we are able to more accurately classify patients and instances as experiencing significant OAG progression. A Kalman filter approach for estimating the true value of OAG biomarkers resulted in data input which improved the accuracy of a logistic regression classification model compared to a model using raw measurements as input. This methodology accounts for process and measurement noise to enable improved discrimination between progression and nonprogression in chronic diseases.

Modeling critical habitat for Flammulated Owls (Otus flammeolus)

Treesearch

David A. Christie; Astrid M. van Woudenberg

1997-01-01

Multiple logistic regression analysis was used to produce a prediction model for Flammulated Owl (Otus flammeolus) breeding habitat within the Kamloops Forest Region in south-central British Columbia. Using the model equation, a pilot habitat prediction map was created within a Geographic Information System (GIS) environment that had a 75.7 percent...

[Optimization of diagnosis indicator selection and inspection plan by 3.0T MRI in breast cancer].

PubMed

Jiang, Zhongbiao; Wang, Yunhua; He, Zhong; Zhang, Lejun; Zheng, Kai

2013-08-01

To optimize 3.0T MRI diagnosis indicator in breast cancer and to select the best MRI scan program. Totally 45 patients with breast cancers were collected, and another 35 patients with benign breast tumor served as the control group. All patients underwent 3.0T MRI, including T1- weighted imaging (T1WI), fat suppression of the T2-weighted imaging (T2WI), diffusion weighted imaging (DWI), 1H magnetic resonance spectroscopy (1H-MRS) and dynamic contrast enhanced (DCE) sequence. With operation pathology results as the gold standard in the diagnosis of breast diseases, the pathological results of benign and malignant served as dependent variables, and the diagnostic indicators of MRI were taken as independent variables. We put all the indicators of MRI examination under Logistic regression analysis, established the Logistic model, and optimized the diagnosis indicators of MRI examination to further improve MRI scan of breast cancer. By Logistic regression analysis, some indicators were selected in the equation, including the edge feature of the tumor, the time-signal intensity curve (TIC) type and the apparent diffusion coefficient (ADC) value when b=500 s/mm2. The regression equation was Logit (P)=-21.936+20.478X6+3.267X7+ 21.488X3. Valuable indicators in the diagnosis of breast cancer are the edge feature of the tumor, the TIC type and the ADC value when b=500 s/mm2. Combining conventional MRI scan, DWI and dynamic enhanced MRI is a better examination program, while MRS is the complementary program when diagnosis is difficult.

A logistic regression equation for estimating the probability of a stream flowing perennially in Massachusetts

USGS Publications Warehouse

Bent, Gardner C.; Archfield, Stacey A.

2002-01-01

A logistic regression equation was developed for estimating the probability of a stream flowing perennially at a specific site in Massachusetts. The equation provides city and town conservation commissions and the Massachusetts Department of Environmental Protection with an additional method for assessing whether streams are perennial or intermittent at a specific site in Massachusetts. This information is needed to assist these environmental agencies, who administer the Commonwealth of Massachusetts Rivers Protection Act of 1996, which establishes a 200-foot-wide protected riverfront area extending along the length of each side of the stream from the mean annual high-water line along each side of perennial streams, with exceptions in some urban areas. The equation was developed by relating the verified perennial or intermittent status of a stream site to selected basin characteristics of naturally flowing streams (no regulation by dams, surface-water withdrawals, ground-water withdrawals, diversion, waste-water discharge, and so forth) in Massachusetts. Stream sites used in the analysis were identified as perennial or intermittent on the basis of review of measured streamflow at sites throughout Massachusetts and on visual observation at sites in the South Coastal Basin, southeastern Massachusetts. Measured or observed zero flow(s) during months of extended drought as defined by the 310 Code of Massachusetts Regulations (CMR) 10.58(2)(a) were not considered when designating the perennial or intermittent status of a stream site. The database used to develop the equation included a total of 305 stream sites (84 intermittent- and 89 perennial-stream sites in the State, and 50 intermittent- and 82 perennial-stream sites in the South Coastal Basin). Stream sites included in the database had drainage areas that ranged from 0.14 to 8.94 square miles in the State and from 0.02 to 7.00 square miles in the South Coastal Basin.Results of the logistic regression analysis indicate that the probability of a stream flowing perennially at a specific site in Massachusetts can be estimated as a function of (1) drainage area (cube root), (2) drainage density, (3) areal percentage of stratified-drift deposits (square root), (4) mean basin slope, and (5) location in the South Coastal Basin or the remainder of the State. Although the equation developed provides an objective means for estimating the probability of a stream flowing perennially at a specific site, the reliability of the equation is constrained by the data used to develop the equation. The equation may not be reliable for (1) drainage areas less than 0.14 square mile in the State or less than 0.02 square mile in the South Coastal Basin, (2) streams with losing reaches, or (3) streams draining the southern part of the South Coastal Basin and the eastern part of the Buzzards Bay Basin and the entire area of Cape Cod and the Islands Basins.

Process model comparison and transferability across bioreactor scales and modes of operation for a mammalian cell bioprocess.

PubMed

Craven, Stephen; Shirsat, Nishikant; Whelan, Jessica; Glennon, Brian

2013-01-01

A Monod kinetic model, logistic equation model, and statistical regression model were developed for a Chinese hamster ovary cell bioprocess operated under three different modes of operation (batch, bolus fed-batch, and continuous fed-batch) and grown on two different bioreactor scales (3 L bench-top and 15 L pilot-scale). The Monod kinetic model was developed for all modes of operation under study and predicted cell density, glucose glutamine, lactate, and ammonia concentrations well for the bioprocess. However, it was computationally demanding due to the large number of parameters necessary to produce a good model fit. The transferability of the Monod kinetic model structure and parameter set across bioreactor scales and modes of operation was investigated and a parameter sensitivity analysis performed. The experimentally determined parameters had the greatest influence on model performance. They changed with scale and mode of operation, but were easily calculated. The remaining parameters, which were fitted using a differential evolutionary algorithm, were not as crucial. Logistic equation and statistical regression models were investigated as alternatives to the Monod kinetic model. They were less computationally intensive to develop due to the absence of a large parameter set. However, modeling of the nutrient and metabolite concentrations proved to be troublesome due to the logistic equation model structure and the inability of both models to incorporate a feed. The complexity, computational load, and effort required for model development has to be balanced with the necessary level of model sophistication when choosing which model type to develop for a particular application. Copyright © 2012 American Institute of Chemical Engineers (AIChE).

Prediction of spatially explicit rainfall intensity-duration thresholds for post-fire debris-flow generation in the western United States

NASA Astrophysics Data System (ADS)

Staley, Dennis; Negri, Jacquelyn; Kean, Jason

2016-04-01

Population expansion into fire-prone steeplands has resulted in an increase in post-fire debris-flow risk in the western United States. Logistic regression methods for determining debris-flow likelihood and the calculation of empirical rainfall intensity-duration thresholds for debris-flow initiation represent two common approaches for characterizing hazard and reducing risk. Logistic regression models are currently being used to rapidly assess debris-flow hazard in response to design storms of known intensities (e.g. a 10-year recurrence interval rainstorm). Empirical rainfall intensity-duration thresholds comprise a major component of the United States Geological Survey (USGS) and the National Weather Service (NWS) debris-flow early warning system at a regional scale in southern California. However, these two modeling approaches remain independent, with each approach having limitations that do not allow for synergistic local-scale (e.g. drainage-basin scale) characterization of debris-flow hazard during intense rainfall. The current logistic regression equations consider rainfall a unique independent variable, which prevents the direct calculation of the relation between rainfall intensity and debris-flow likelihood. Regional (e.g. mountain range or physiographic province scale) rainfall intensity-duration thresholds fail to provide insight into the basin-scale variability of post-fire debris-flow hazard and require an extensive database of historical debris-flow occurrence and rainfall characteristics. Here, we present a new approach that combines traditional logistic regression and intensity-duration threshold methodologies. This method allows for local characterization of both the likelihood that a debris-flow will occur at a given rainfall intensity, the direct calculation of the rainfall rates that will result in a given likelihood, and the ability to calculate spatially explicit rainfall intensity-duration thresholds for debris-flow generation in recently burned areas. Our approach synthesizes the two methods by incorporating measured rainfall intensity into each model variable (based on measures of topographic steepness, burn severity and surface properties) within the logistic regression equation. This approach provides a more realistic representation of the relation between rainfall intensity and debris-flow likelihood, as likelihood values asymptotically approach zero when rainfall intensity approaches 0 mm/h, and increase with more intense rainfall. Model performance was evaluated by comparing predictions to several existing regional thresholds. The model, based upon training data collected in southern California, USA, has proven to accurately predict rainfall intensity-duration thresholds for other areas in the western United States not included in the original training dataset. In addition, the improved logistic regression model shows promise for emergency planning purposes and real-time, site-specific early warning. With further validation, this model may permit the prediction of spatially-explicit intensity-duration thresholds for debris-flow generation in areas where empirically derived regional thresholds do not exist. This improvement would permit the expansion of the early-warning system into other regions susceptible to post-fire debris flow.

A revised logistic regression equation and an automated procedure for mapping the probability of a stream flowing perennially in Massachusetts

USGS Publications Warehouse

Bent, Gardner C.; Steeves, Peter A.

2006-01-01

A revised logistic regression equation and an automated procedure were developed for mapping the probability of a stream flowing perennially in Massachusetts. The equation provides city and town conservation commissions and the Massachusetts Department of Environmental Protection a method for assessing whether streams are intermittent or perennial at a specific site in Massachusetts by estimating the probability of a stream flowing perennially at that site. This information could assist the environmental agencies who administer the Commonwealth of Massachusetts Rivers Protection Act of 1996, which establishes a 200-foot-wide protected riverfront area extending from the mean annual high-water line along each side of a perennial stream, with exceptions for some urban areas. The equation was developed by relating the observed intermittent or perennial status of a stream site to selected basin characteristics of naturally flowing streams (defined as having no regulation by dams, surface-water withdrawals, ground-water withdrawals, diversion, wastewater discharge, and so forth) in Massachusetts. This revised equation differs from the equation developed in a previous U.S. Geological Survey study in that it is solely based on visual observations of the intermittent or perennial status of stream sites across Massachusetts and on the evaluation of several additional basin and land-use characteristics as potential explanatory variables in the logistic regression analysis. The revised equation estimated more accurately the intermittent or perennial status of the observed stream sites than the equation from the previous study. Stream sites used in the analysis were identified as intermittent or perennial based on visual observation during low-flow periods from late July through early September 2001. The database of intermittent and perennial streams included a total of 351 naturally flowing (no regulation) sites, of which 85 were observed to be intermittent and 266 perennial. Stream sites included in the database had drainage areas that ranged from 0.04 to 10.96 square miles. Of the 66 stream sites with drainage areas greater than 2.00 square miles, 2 sites were intermittent and 64 sites were perennial. Thus, stream sites with drainage areas greater than 2.00 square miles were assumed to flow perennially, and the database used to develop the logistic regression equation included only those stream sites with drainage areas less than 2.00 square miles. The database for the equation included 285 stream sites that had drainage areas less than 2.00 square miles, of which 83 sites were intermittent and 202 sites were perennial. Results of the logistic regression analysis indicate that the probability of a stream flowing perennially at a specific site in Massachusetts can be estimated as a function of four explanatory variables: (1) drainage area (natural logarithm), (2) areal percentage of sand and gravel deposits, (3) areal percentage of forest land, and (4) region of the state (eastern region or western region). Although the equation provides an objective means of determining the probability of a stream flowing perennially at a specific site, the reliability of the equation is constrained by the data used in its development. The equation is not recommended for (1) losing stream reaches or (2) streams whose ground-water contributing areas do not coincide with their surface-water drainage areas, such as many streams draining the Southeast Coastal Region-the southern part of the South Coastal Basin, the eastern part of the Buzzards Bay Basin, and the entire area of the Cape Cod and the Islands Basins. If the equation were used on a regulated stream site, the estimated intermittent or perennial status would reflect the natural flow conditions for that site. An automated mapping procedure was developed to determine the intermittent or perennial status of stream sites along reaches throughout a basin. The procedure delineates the drainage area boundaries, determines values for the four explanatory variables, and solves the equation for estimating the probability of a stream flowing perennially at two locations on a headwater (first-order) stream reach-one near its confluence or end point and one near its headwaters or start point. The automated procedure then determines the intermittent or perennial status of the reach on the basis of the calculated probability values and a probability cutpoint (a stream is considered to flow perennially at a cutpoint of 0.56 or greater for this study) for the two locations or continues to loop upstream or downstream between locations less than and greater than the cutpoint of 0.56 to determine the transition point from an intermittent to a perennial stream. If the first-order stream reach is determined to be intermittent, the procedure moves to the next downstream reach and repeats the same process. The automated procedure then moves to the next first-order stream and repeats the process until the entire basin is mapped. A map of the intermittent and perennial stream reaches in the Shawsheen River Basin is provided on a CD-ROM that accompanies this report. The CD-ROM also contains ArcReader 9.0, a freeware product, that allows a user to zoom in and out, set a scale, pan, turn on and off map layers (such as a USGS topographic map), and print a map of the stream site with a scale bar. Maps of the intermittent and perennial stream reaches in Massachusetts will provide city and town conservation commissions and the Massachusetts Department of Environmental Protection with an additional method for assessing the intermittent or perennial status of stream sites.

Peak oxygen consumption measured during the stair-climbing test in lung resection candidates.

PubMed

Brunelli, Alessandro; Xiumé, Francesco; Refai, Majed; Salati, Michele; Di Nunzio, Luca; Pompili, Cecilia; Sabbatini, Armando

2010-01-01

The stair-climbing test is commonly used in the preoperative evaluation of lung resection candidates, but it is difficult to standardize and provides little physiologic information on the performance. To verify the association between the altitude and the V(O2peak) measured during the stair-climbing test. 109 consecutive candidates for lung resection performed a symptom-limited stair-climbing test with direct breath-by-breath measurement of V(O2peak) by a portable gas analyzer. Stepwise logistic regression and bootstrap analyses were used to verify the association of several perioperative variables with a V(O2peak) <15 ml/kg/min. Subsequently, multiple regression analysis was also performed to develop an equation to estimate V(O2peak) from stair-climbing parameters and other patient-related variables. 56% of patients climbing <14 m had a V(O2peak) <15 ml/kg/min, whereas 98% of those climbing >22 m had a V(O2peak) >15 ml/kg/min. The altitude reached at stair-climbing test resulted in the only significant predictor of a V(O2peak) <15 ml/kg/min after logistic regression analysis. Multiple regression analysis yielded an equation to estimate V(O2peak) factoring altitude (p < 0.0001), speed of ascent (p = 0.005) and body mass index (p = 0.0008). There was an association between altitude and V(O2peak) measured during the stair-climbing test. Most of the patients climbing more than 22 m are able to generate high values of V(O2peak) and can proceed to surgery without any additional tests. All others need to be referred for a formal cardiopulmonary exercise test. In addition, we were able to generate an equation to estimate V(O2peak), which could assist in streamlining the preoperative workup and could be used across different settings to standardize this test. Copyright (c) 2010 S. Karger AG, Basel.

Analytical solution of Luedeking-Piret equation for a batch fermentation obeying Monod growth kinetics.

PubMed

Garnier, Alain; Gaillet, Bruno

2015-12-01

Not so many fermentation mathematical models allow analytical solutions of batch process dynamics. The most widely used is the combination of the logistic microbial growth kinetics with Luedeking-Piret bioproduct synthesis relation. However, the logistic equation is principally based on formalistic similarities and only fits a limited range of fermentation types. In this article, we have developed an analytical solution for the combination of Monod growth kinetics with Luedeking-Piret relation, which can be identified by linear regression and used to simulate batch fermentation evolution. Two classical examples are used to show the quality of fit and the simplicity of the method proposed. A solution for the combination of Haldane substrate-limited growth model combined with Luedeking-Piret relation is also provided. These models could prove useful for the analysis of fermentation data in industry as well as academia. © 2015 Wiley Periodicals, Inc.

Comparative study of contrast-enhanced ultrasound qualitative and quantitative analysis for identifying benign and malignant breast tumor lumps.

PubMed

Liu, Jian; Gao, Yun-Hua; Li, Ding-Dong; Gao, Yan-Chun; Hou, Ling-Mi; Xie, Ting

2014-01-01

To compare the value of contrast-enhanced ultrasound (CEUS) qualitative and quantitative analysis in the identification of breast tumor lumps. Qualitative and quantitative indicators of CEUS for 73 cases of breast tumor lumps were retrospectively analyzed by univariate and multivariate approaches. Logistic regression was applied and ROC curves were drawn for evaluation and comparison. The CEUS qualitative indicator-generated regression equation contained three indicators, namely enhanced homogeneity, diameter line expansion and peak intensity grading, which demonstrated prediction accuracy for benign and malignant breast tumor lumps of 91.8%; the quantitative indicator-generated regression equation only contained one indicator, namely the relative peak intensity, and its prediction accuracy was 61.5%. The corresponding areas under the ROC curve for qualitative and quantitative analyses were 91.3% and 75.7%, respectively, which exhibited a statistically significant difference by the Z test (P<0.05). The ability of CEUS qualitative analysis to identify breast tumor lumps is better than with quantitative analysis.

Development and validation of a mortality risk model for pediatric sepsis.

PubMed

Chen, Mengshi; Lu, Xiulan; Hu, Li; Liu, Pingping; Zhao, Wenjiao; Yan, Haipeng; Tang, Liang; Zhu, Yimin; Xiao, Zhenghui; Chen, Lizhang; Tan, Hongzhuan

2017-05-01

Pediatric sepsis is a burdensome public health problem. Assessing the mortality risk of pediatric sepsis patients, offering effective treatment guidance, and improving prognosis to reduce mortality rates, are crucial.We extracted data derived from electronic medical records of pediatric sepsis patients that were collected during the first 24 hours after admission to the pediatric intensive care unit (PICU) of the Hunan Children's hospital from January 2012 to June 2014. A total of 788 children were randomly divided into a training (592, 75%) and validation group (196, 25%). The risk factors for mortality among these patients were identified by conducting multivariate logistic regression in the training group. Based on the established logistic regression equation, the logit probabilities for all patients (in both groups) were calculated to verify the model's internal and external validities.According to the training group, 6 variables (brain natriuretic peptide, albumin, total bilirubin, D-dimer, lactate levels, and mechanical ventilation in 24 hours) were included in the final logistic regression model. The areas under the curves of the model were 0.854 (0.826, 0.881) and 0.844 (0.816, 0.873) in the training and validation groups, respectively.The Mortality Risk Model for Pediatric Sepsis we established in this study showed acceptable accuracy to predict the mortality risk in pediatric sepsis patients.

Development and validation of a mortality risk model for pediatric sepsis

PubMed Central

Chen, Mengshi; Lu, Xiulan; Hu, Li; Liu, Pingping; Zhao, Wenjiao; Yan, Haipeng; Tang, Liang; Zhu, Yimin; Xiao, Zhenghui; Chen, Lizhang; Tan, Hongzhuan

2017-01-01

Abstract Pediatric sepsis is a burdensome public health problem. Assessing the mortality risk of pediatric sepsis patients, offering effective treatment guidance, and improving prognosis to reduce mortality rates, are crucial. We extracted data derived from electronic medical records of pediatric sepsis patients that were collected during the first 24 hours after admission to the pediatric intensive care unit (PICU) of the Hunan Children's hospital from January 2012 to June 2014. A total of 788 children were randomly divided into a training (592, 75%) and validation group (196, 25%). The risk factors for mortality among these patients were identified by conducting multivariate logistic regression in the training group. Based on the established logistic regression equation, the logit probabilities for all patients (in both groups) were calculated to verify the model's internal and external validities. According to the training group, 6 variables (brain natriuretic peptide, albumin, total bilirubin, D-dimer, lactate levels, and mechanical ventilation in 24 hours) were included in the final logistic regression model. The areas under the curves of the model were 0.854 (0.826, 0.881) and 0.844 (0.816, 0.873) in the training and validation groups, respectively. The Mortality Risk Model for Pediatric Sepsis we established in this study showed acceptable accuracy to predict the mortality risk in pediatric sepsis patients. PMID:28514310

Binomial outcomes in dataset with some clusters of size two: can the dependence of twins be accounted for? A simulation study comparing the reliability of statistical methods based on a dataset of preterm infants.

PubMed

Sauzet, Odile; Peacock, Janet L

2017-07-20

The analysis of perinatal outcomes often involves datasets with some multiple births. These are datasets mostly formed of independent observations and a limited number of clusters of size two (twins) and maybe of size three or more. This non-independence needs to be accounted for in the statistical analysis. Using simulated data based on a dataset of preterm infants we have previously investigated the performance of several approaches to the analysis of continuous outcomes in the presence of some clusters of size two. Mixed models have been developed for binomial outcomes but very little is known about their reliability when only a limited number of small clusters are present. Using simulated data based on a dataset of preterm infants we investigated the performance of several approaches to the analysis of binomial outcomes in the presence of some clusters of size two. Logistic models, several methods of estimation for the logistic random intercept models and generalised estimating equations were compared. The presence of even a small percentage of twins means that a logistic regression model will underestimate all parameters but a logistic random intercept model fails to estimate the correlation between siblings if the percentage of twins is too small and will provide similar estimates to logistic regression. The method which seems to provide the best balance between estimation of the standard error and the parameter for any percentage of twins is the generalised estimating equations. This study has shown that the number of covariates or the level two variance do not necessarily affect the performance of the various methods used to analyse datasets containing twins but when the percentage of small clusters is too small, mixed models cannot capture the dependence between siblings.

A comparison between univariate probabilistic and multivariate (logistic regression) methods for landslide susceptibility analysis: the example of the Febbraro valley (Northern Alps, Italy)

NASA Astrophysics Data System (ADS)

Rossi, M.; Apuani, T.; Felletti, F.

2009-04-01

The aim of this paper is to compare the results of two statistical methods for landslide susceptibility analysis: 1) univariate probabilistic method based on landslide susceptibility index, 2) multivariate method (logistic regression). The study area is the Febbraro valley, located in the central Italian Alps, where different types of metamorphic rocks croup out. On the eastern part of the studied basin a quaternary cover represented by colluvial and secondarily, by glacial deposits, is dominant. In this study 110 earth flows, mainly located toward NE portion of the catchment, were analyzed. They involve only the colluvial deposits and their extension mainly ranges from 36 to 3173 m2. Both statistical methods require to establish a spatial database, in which each landslide is described by several parameters that can be assigned using a main scarp central point of landslide. The spatial database is constructed using a Geographical Information System (GIS). Each landslide is described by several parameters corresponding to the value of main scarp central point of the landslide. Based on bibliographic review a total of 15 predisposing factors were utilized. The width of the intervals, in which the maps of the predisposing factors have to be reclassified, has been defined assuming constant intervals to: elevation (100 m), slope (5 °), solar radiation (0.1 MJ/cm2/year), profile curvature (1.2 1/m), tangential curvature (2.2 1/m), drainage density (0.5), lineament density (0.00126). For the other parameters have been used the results of the probability-probability plots analysis and the statistical indexes of landslides site. In particular slope length (0 ÷ 2, 2 ÷ 5, 5 ÷ 10, 10 ÷ 20, 20 ÷ 35, 35 ÷ 260), accumulation flow (0 ÷ 1, 1 ÷ 2, 2 ÷ 5, 5 ÷ 12, 12 ÷ 60, 60 ÷27265), Topographic Wetness Index 0 ÷ 0.74, 0.74 ÷ 1.94, 1.94 ÷ 2.62, 2.62 ÷ 3.48, 3.48 ÷ 6,00, 6.00 ÷ 9.44), Stream Power Index (0 ÷ 0.64, 0.64 ÷ 1.28, 1.28 ÷ 1.81, 1.81 ÷ 4.20, 4.20 ÷ 9.40). Geological map and land use map were also used, considering geological and land use properties as categorical variables. Appling the univariate probabilistic method the Landslide Susceptibility Index (LSI) is defined as the sum of the ratio Ra/Rb calculated for each predisposing factor, where Ra is the ratio between number of pixel of class and the total number of pixel of the study area, and Rb is the ratio between number of landslides respect to the pixel number of the interval area. From the analysis of the Ra/Rb ratio the relationship between landslide occurrence and predisposing factors were defined. Then the equation of LSI was used in GIS to trace the landslide susceptibility maps. The multivariate method for landslide susceptibility analysis, based on logistic regression, was performed starting from the density maps of the predisposing factors, calculated with the intervals defined above using the equation Rb/Rbtot, where Rbtot is a sum of all Rb values. Using stepwise forward algorithms the logistic regression was performed in two successive steps: first a univariate logistic regression is used to choose the most significant predisposing factors, then the multivariate logistic regression can be performed. The univariate regression highlighted the importance of the following factors: elevation, accumulation flow, drainage density, lineament density, geology and land use. When the multivariate regression was applied the number of controlling factors was reduced neglecting the geological properties. The resulting final susceptibility equation is: P = 1 / (1 + exp-(6.46-22.34*elevation-5.33*accumulation flow-7.99* drainage density-4.47*lineament density-17.31*land use)) and using this equation the susceptibility maps were obtained. To easy compare the results of the two methodologies, the susceptibility maps were reclassified in five susceptibility intervals (very high, high, moderate, low and very low) using natural breaks. Then the maps were validated using two cumulative distribution curves, one related to the landslides (number of landslides in each susceptibility class) and one to the basin (number of pixel covering each class). Comparing the curves for each method, it results that the two approaches (univariate and multivariate) are appropriate, providing acceptable results. In both maps the distribution of high susceptibility condition is mainly localized on the left slope of the catchment in agreement with the field evidences. The comparison between the methods was obtained by subtraction of the two maps. This operation shows that about 40% of the basin is classified by the same class of susceptibility. In general the univariate probabilistic method tends to overestimate the areal extension of the high susceptibility class with respect to the maps obtained by the logistic regression method.

Multivariate logistic regression for predicting total culturable virus presence at the intake of a potable-water treatment plant: novel application of the atypical coliform/total coliform ratio.

PubMed

Black, L E; Brion, G M; Freitas, S J

2007-06-01

Predicting the presence of enteric viruses in surface waters is a complex modeling problem. Multiple water quality parameters that indicate the presence of human fecal material, the load of fecal material, and the amount of time fecal material has been in the environment are needed. This paper presents the results of a multiyear study of raw-water quality at the inlet of a potable-water plant that related 17 physical, chemical, and biological indices to the presence of enteric viruses as indicated by cytopathic changes in cell cultures. It was found that several simple, multivariate logistic regression models that could reliably identify observations of the presence or absence of total culturable virus could be fitted. The best models developed combined a fecal age indicator (the atypical coliform [AC]/total coliform [TC] ratio), the detectable presence of a human-associated sterol (epicoprostanol) to indicate the fecal source, and one of several fecal load indicators (the levels of Giardia species cysts, coliform bacteria, and coprostanol). The best fit to the data was found when the AC/TC ratio, the presence of epicoprostanol, and the density of fecal coliform bacteria were input into a simple, multivariate logistic regression equation, resulting in 84.5% and 78.6% accuracies for the identification of the presence and absence of total culturable virus, respectively. The AC/TC ratio was the most influential input variable in all of the models generated, but producing the best prediction required additional input related to the fecal source and the fecal load. The potential for replacing microbial indicators of fecal load with levels of coprostanol was proposed and evaluated by multivariate logistic regression modeling for the presence and absence of virus.

Help-Seeking Intentions and Behaviors among Mainland Chinese College Students: Integrating the Theory of Planned Behavior and Behavioral Model of Health Services Use

ERIC Educational Resources Information Center

Li, Wenjing; Denson, Linley A.; Dorstyn, Diana S.

2017-01-01

This study investigated help-seeking intentions and use of mental health services within a sample of 1128 Mainland Chinese college students (630 males and 498 females; mean age = 20.01 years, SD = 1.48). Results of structural equation modeling and logistic regression analysis suggested that social-cognitive variables had significant effects both…

Objective Lightning Probability Forecasting for Kennedy Space Center and Cape Canaveral Air Force Station

NASA Technical Reports Server (NTRS)

Lambert, Winifred; Wheeler, Mark

2005-01-01

Five logistic regression equations were created that predict the probability of cloud-to-ground lightning occurrence for the day in the KSC/CCAFS area for each month in the warm season. These equations integrated the results from several studies over recent years to improve thunderstorm forecasting at KSC/CCAFS. All of the equations outperform persistence, which is known to outperform NPTI, the current objective tool used in 45 WS lightning forecasting operations. The equations also performed well in other tests. As a result, the new equations will be added to the current set of tools used by the 45 WS to determine the probability of lightning for their daily planning forecast. The results from these equations are meant to be used as first-guess guidance when developing the lightning probability forecast for the day. They provide an objective base from which forecasters can use other observations, model data, consultation with other forecasters, and their own experience to create the final lightning probability for the 1100 UTC briefing.

The effect of service satisfaction and spiritual well-being on the quality of life of patients with schizophrenia.

PubMed

Lanfredi, Mariangela; Candini, Valentina; Buizza, Chiara; Ferrari, Clarissa; Boero, Maria E; Giobbio, Gian M; Goldschmidt, Nicoletta; Greppo, Stefania; Iozzino, Laura; Maggi, Paolo; Melegari, Anna; Pasqualetti, Patrizio; Rossi, Giuseppe; de Girolamo, Giovanni

2014-05-15

Quality of life (QOL) has been considered an important outcome measure in psychiatric research and determinants of QOL have been widely investigated. We aimed at detecting predictors of QOL at baseline and at testing the longitudinal interrelations of the baseline predictors with QOL scores at a 1-year follow-up in a sample of patients living in Residential Facilities (RFs). Logistic regression models were adopted to evaluate the association between WHOQoL-Bref scores and potential determinants of QOL. In addition, all variables significantly associated with QOL domains in the final logistic regression model were included by using the Structural Equation Modeling (SEM). We included 139 patients with a diagnosis of schizophrenia spectrum. In the final logistic regression model level of activity, social support, age, service satisfaction, spiritual well-being and symptoms' severity were identified as predictors of QOL scores at baseline. Longitudinal analyses carried out by SEM showed that 40% of QOL follow-up variability was explained by QOL at baseline, and significant indirect effects toward QOL at follow-up were found for satisfaction with services and for social support. Rehabilitation plans for people with schizophrenia living in RFs should also consider mediators of change in subjective QOL such as satisfaction with mental health services. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

The effect of high leverage points on the logistic ridge regression estimator having multicollinearity

NASA Astrophysics Data System (ADS)

Ariffin, Syaiba Balqish; Midi, Habshah

2014-06-01

This article is concerned with the performance of logistic ridge regression estimation technique in the presence of multicollinearity and high leverage points. In logistic regression, multicollinearity exists among predictors and in the information matrix. The maximum likelihood estimator suffers a huge setback in the presence of multicollinearity which cause regression estimates to have unduly large standard errors. To remedy this problem, a logistic ridge regression estimator is put forward. It is evident that the logistic ridge regression estimator outperforms the maximum likelihood approach for handling multicollinearity. The effect of high leverage points are then investigated on the performance of the logistic ridge regression estimator through real data set and simulation study. The findings signify that logistic ridge regression estimator fails to provide better parameter estimates in the presence of both high leverage points and multicollinearity.

Epidemiological characteristics of reported sporadic and outbreak cases of E. coli O157 in people from Alberta, Canada (2000-2002): methodological challenges of comparing clustered to unclustered data.

PubMed

Pearl, D L; Louie, M; Chui, L; Doré, K; Grimsrud, K M; Martin, S W; Michel, P; Svenson, L W; McEwen, S A

2008-04-01

Using multivariable models, we compared whether there were significant differences between reported outbreak and sporadic cases in terms of their sex, age, and mode and site of disease transmission. We also determined the potential role of administrative, temporal, and spatial factors within these models. We compared a variety of approaches to account for clustering of cases in outbreaks including weighted logistic regression, random effects models, general estimating equations, robust variance estimates, and the random selection of one case from each outbreak. Age and mode of transmission were the only epidemiologically and statistically significant covariates in our final models using the above approaches. Weighing observations in a logistic regression model by the inverse of their outbreak size appeared to be a relatively robust and valid means for modelling these data. Some analytical techniques, designed to account for clustering, had difficulty converging or producing realistic measures of association.

Sample size determination for logistic regression on a logit-normal distribution.

PubMed

Kim, Seongho; Heath, Elisabeth; Heilbrun, Lance

2017-06-01

Although the sample size for simple logistic regression can be readily determined using currently available methods, the sample size calculation for multiple logistic regression requires some additional information, such as the coefficient of determination ([Formula: see text]) of a covariate of interest with other covariates, which is often unavailable in practice. The response variable of logistic regression follows a logit-normal distribution which can be generated from a logistic transformation of a normal distribution. Using this property of logistic regression, we propose new methods of determining the sample size for simple and multiple logistic regressions using a normal transformation of outcome measures. Simulation studies and a motivating example show several advantages of the proposed methods over the existing methods: (i) no need for [Formula: see text] for multiple logistic regression, (ii) available interim or group-sequential designs, and (iii) much smaller required sample size.

A comparison of Cox and logistic regression for use in genome-wide association studies of cohort and case-cohort design.

PubMed

Staley, James R; Jones, Edmund; Kaptoge, Stephen; Butterworth, Adam S; Sweeting, Michael J; Wood, Angela M; Howson, Joanna M M

2017-06-01

Logistic regression is often used instead of Cox regression to analyse genome-wide association studies (GWAS) of single-nucleotide polymorphisms (SNPs) and disease outcomes with cohort and case-cohort designs, as it is less computationally expensive. Although Cox and logistic regression models have been compared previously in cohort studies, this work does not completely cover the GWAS setting nor extend to the case-cohort study design. Here, we evaluated Cox and logistic regression applied to cohort and case-cohort genetic association studies using simulated data and genetic data from the EPIC-CVD study. In the cohort setting, there was a modest improvement in power to detect SNP-disease associations using Cox regression compared with logistic regression, which increased as the disease incidence increased. In contrast, logistic regression had more power than (Prentice weighted) Cox regression in the case-cohort setting. Logistic regression yielded inflated effect estimates (assuming the hazard ratio is the underlying measure of association) for both study designs, especially for SNPs with greater effect on disease. Given logistic regression is substantially more computationally efficient than Cox regression in both settings, we propose a two-step approach to GWAS in cohort and case-cohort studies. First to analyse all SNPs with logistic regression to identify associated variants below a pre-defined P-value threshold, and second to fit Cox regression (appropriately weighted in case-cohort studies) to those identified SNPs to ensure accurate estimation of association with disease.

The crux of the method: assumptions in ordinary least squares and logistic regression.

PubMed

Long, Rebecca G

2008-10-01

Logistic regression has increasingly become the tool of choice when analyzing data with a binary dependent variable. While resources relating to the technique are widely available, clear discussions of why logistic regression should be used in place of ordinary least squares regression are difficult to find. The current paper compares and contrasts the assumptions of ordinary least squares with those of logistic regression and explains why logistic regression's looser assumptions make it adept at handling violations of the more important assumptions in ordinary least squares.

Using Dominance Analysis to Determine Predictor Importance in Logistic Regression

ERIC Educational Resources Information Center

Azen, Razia; Traxel, Nicole

2009-01-01

This article proposes an extension of dominance analysis that allows researchers to determine the relative importance of predictors in logistic regression models. Criteria for choosing logistic regression R[superscript 2] analogues were determined and measures were selected that can be used to perform dominance analysis in logistic regression. A…

Estimating irrigation water use in the humid eastern United States

USGS Publications Warehouse

Levin, Sara B.; Zarriello, Phillip J.

2013-01-01

Accurate accounting of irrigation water use is an important part of the U.S. Geological Survey National Water-Use Information Program and the WaterSMART initiative to help maintain sustainable water resources in the Nation. Irrigation water use in the humid eastern United States is not well characterized because of inadequate reporting and wide variability associated with climate, soils, crops, and farming practices. To better understand irrigation water use in the eastern United States, two types of predictive models were developed and compared by using metered irrigation water-use data for corn, cotton, peanut, and soybean crops in Georgia and turf farms in Rhode Island. Reliable metered irrigation data were limited to these areas. The first predictive model that was developed uses logistic regression to predict the occurrence of irrigation on the basis of antecedent climate conditions. Logistic regression equations were developed for corn, cotton, peanut, and soybean crops by using weekly irrigation water-use data from 36 metered sites in Georgia in 2009 and 2010 and turf farms in Rhode Island from 2000 to 2004. For the weeks when irrigation was predicted to take place, the irrigation water-use volume was estimated by multiplying the average metered irrigation application rate by the irrigated acreage for a given crop. The second predictive model that was developed is a crop-water-demand model that uses a daily soil water balance to estimate the water needs of a crop on a given day based on climate, soil, and plant properties. Crop-water-demand models were developed independently of reported irrigation water-use practices and relied on knowledge of plant properties that are available in the literature. Both modeling approaches require accurate accounting of irrigated area and crop type to estimate total irrigation water use. Water-use estimates from both modeling methods were compared to the metered irrigation data from Rhode Island and Georgia that were used to develop the models as well as two independent validation datasets from Georgia and Virginia that were not used in model development. Irrigation water-use estimates from the logistic regression method more closely matched mean reported irrigation rates than estimates from the crop-water-demand model when compared to the irrigation data used to develop the equations. The root mean squared errors (RMSEs) for the logistic regression estimates of mean annual irrigation ranged from 0.3 to 2.0 inches (in.) for the five crop types; RMSEs for the crop-water-demand models ranged from 1.4 to 3.9 in. However, when the models were applied and compared to the independent validation datasets from southwest Georgia from 2010, and from Virginia from 1999 to 2007, the crop-water-demand model estimates were as good as or better at predicting the mean irrigation volume than the logistic regression models for most crop types. RMSEs for logistic regression estimates of mean annual irrigation ranged from 1.0 to 7.0 in. for validation data from Georgia and from 1.8 to 4.9 in. for validation data from Virginia; RMSEs for crop-water-demand model estimates ranged from 2.1 to 5.8 in. for Georgia data and from 2.0 to 3.9 in. for Virginia data. In general, regression-based models performed better in areas that had quality daily or weekly irrigation data from which the regression equations were developed; however, the regression models were less reliable than the crop-water-demand models when applied outside the area for which they were developed. In most eastern coastal states that do not have quality irrigation data, the crop-water-demand model can be used more reliably. The development of predictive models of irrigation water use in this study was hindered by a lack of quality irrigation data. Many mid-Atlantic and New England states do not require irrigation water use to be reported. A survey of irrigation data from 14 eastern coastal states from Maine to Georgia indicated that, with the exception of the data in Georgia, irrigation data in the states that do require reporting commonly did not contain requisite ancillary information such as irrigated area or crop type, lacked precision, or were at an aggregated temporal scale making them unsuitable for use in the development of predictive models. Confidence in the reliability of either modeling method is affected by uncertainty in the reported data from which the models were developed or validated. Only through additional collection of quality data and further study can the accuracy and uncertainty of irrigation water-use estimates be improved in the humid eastern United States.

Applying Kaplan-Meier to Item Response Data

ERIC Educational Resources Information Center

McNeish, Daniel

2018-01-01

Some IRT models can be equivalently modeled in alternative frameworks such as logistic regression. Logistic regression can also model time-to-event data, which concerns the probability of an event occurring over time. Using the relation between time-to-event models and logistic regression and the relation between logistic regression and IRT, this…

A secure distributed logistic regression protocol for the detection of rare adverse drug events

PubMed Central

El Emam, Khaled; Samet, Saeed; Arbuckle, Luk; Tamblyn, Robyn; Earle, Craig; Kantarcioglu, Murat

2013-01-01

Background There is limited capacity to assess the comparative risks of medications after they enter the market. For rare adverse events, the pooling of data from multiple sources is necessary to have the power and sufficient population heterogeneity to detect differences in safety and effectiveness in genetic, ethnic and clinically defined subpopulations. However, combining datasets from different data custodians or jurisdictions to perform an analysis on the pooled data creates significant privacy concerns that would need to be addressed. Existing protocols for addressing these concerns can result in reduced analysis accuracy and can allow sensitive information to leak. Objective To develop a secure distributed multi-party computation protocol for logistic regression that provides strong privacy guarantees. Methods We developed a secure distributed logistic regression protocol using a single analysis center with multiple sites providing data. A theoretical security analysis demonstrates that the protocol is robust to plausible collusion attacks and does not allow the parties to gain new information from the data that are exchanged among them. The computational performance and accuracy of the protocol were evaluated on simulated datasets. Results The computational performance scales linearly as the dataset sizes increase. The addition of sites results in an exponential growth in computation time. However, for up to five sites, the time is still short and would not affect practical applications. The model parameters are the same as the results on pooled raw data analyzed in SAS, demonstrating high model accuracy. Conclusion The proposed protocol and prototype system would allow the development of logistic regression models in a secure manner without requiring the sharing of personal health information. This can alleviate one of the key barriers to the establishment of large-scale post-marketing surveillance programs. We extended the secure protocol to account for correlations among patients within sites through generalized estimating equations, and to accommodate other link functions by extending it to generalized linear models. PMID:22871397

A secure distributed logistic regression protocol for the detection of rare adverse drug events.

PubMed

El Emam, Khaled; Samet, Saeed; Arbuckle, Luk; Tamblyn, Robyn; Earle, Craig; Kantarcioglu, Murat

2013-05-01

There is limited capacity to assess the comparative risks of medications after they enter the market. For rare adverse events, the pooling of data from multiple sources is necessary to have the power and sufficient population heterogeneity to detect differences in safety and effectiveness in genetic, ethnic and clinically defined subpopulations. However, combining datasets from different data custodians or jurisdictions to perform an analysis on the pooled data creates significant privacy concerns that would need to be addressed. Existing protocols for addressing these concerns can result in reduced analysis accuracy and can allow sensitive information to leak. To develop a secure distributed multi-party computation protocol for logistic regression that provides strong privacy guarantees. We developed a secure distributed logistic regression protocol using a single analysis center with multiple sites providing data. A theoretical security analysis demonstrates that the protocol is robust to plausible collusion attacks and does not allow the parties to gain new information from the data that are exchanged among them. The computational performance and accuracy of the protocol were evaluated on simulated datasets. The computational performance scales linearly as the dataset sizes increase. The addition of sites results in an exponential growth in computation time. However, for up to five sites, the time is still short and would not affect practical applications. The model parameters are the same as the results on pooled raw data analyzed in SAS, demonstrating high model accuracy. The proposed protocol and prototype system would allow the development of logistic regression models in a secure manner without requiring the sharing of personal health information. This can alleviate one of the key barriers to the establishment of large-scale post-marketing surveillance programs. We extended the secure protocol to account for correlations among patients within sites through generalized estimating equations, and to accommodate other link functions by extending it to generalized linear models.

Logistic regression analysis to predict Medical Licensing Examination of Thailand (MLET) Step1 success or failure.

PubMed

Wanvarie, Samkaew; Sathapatayavongs, Boonmee

2007-09-01

The aim of this paper was to assess factors that predict students' performance in the Medical Licensing Examination of Thailand (MLET) Step1 examination. The hypothesis was that demographic factors and academic records would predict the students' performance in the Step1 Licensing Examination. A logistic regression analysis of demographic factors (age, sex and residence) and academic records [high school grade point average (GPA), National University Entrance Examination Score and GPAs of the pre-clinical years] with the MLET Step1 outcome was accomplished using the data of 117 third-year Ramathibodi medical students. Twenty-three (19.7%) students failed the MLET Step1 examination. Stepwise logistic regression analysis showed that the significant predictors of MLET Step1 success/failure were residence background and GPAs of the second and third preclinical years. For students whose sophomore and third-year GPAs increased by an average of 1 point, the odds of passing the MLET Step1 examination increased by a factor of 16.3 and 12.8 respectively. The minimum GPAs for students from urban and rural backgrounds to pass the examination were estimated from the equation (2.35 vs 2.65 from 4.00 scale). Students from rural backgrounds and/or low-grade point averages in their second and third preclinical years of medical school are at risk of failing the MLET Step1 examination. They should be given intensive tutorials during the second and third pre-clinical years.

Measurements of the talus in the assessment of population affinity.

PubMed

Bidmos, Mubarak A; Dayal, Manisha R; Adegboye, Oyelola A

2018-06-01

As part of their routine work, forensic anthropologists are expected to report population affinity as part of the biological profile of an individual. The skull is the most widely used bone for the estimation of population affinity but it is not always present in a forensic case. Thus, other bones that preserve well have been shown to give a good indication of either the sex or population affinity of an individual. In this study, the potential of measurements of the talus was investigated for the purpose of estimating population affinity in South Africans. Nine measurements from two hundred and twenty tali of South African Africans (SAA) and South African Whites (SAW) from the Raymond A. Dart Collection of Human Skeletons were used. Direct and step-wise discriminant function and logistic regression analyses were carried out using SPSS and SAS. Talar length was the best single variable for discriminating between these two groups for males while in females the head height was the best single predictor. Average accuracies for correct population affinity classification using logistic regression analysis were higher than those obtained from discriminant function analysis. This study was the first of its type to employ discriminant function analyses and logistic regression analyses to estimate the population affinity of an individual from the talus. Thus these equations can now be used by South African anthropologists when estimating the population affinity of dismembered or damaged or incomplete skeletal remains of SAA and SAW. Copyright © 2018 Elsevier B.V. All rights reserved.

[Formulation of combined predictive indicators using logistic regression model in predicting sepsis and prognosis].

PubMed

Duan, Liwei; Zhang, Sheng; Lin, Zhaofen

2017-02-01

To explore the method and performance of using multiple indices to diagnose sepsis and to predict the prognosis of severe ill patients. Critically ill patients at first admission to intensive care unit (ICU) of Changzheng Hospital, Second Military Medical University, from January 2014 to September 2015 were enrolled if the following conditions were satisfied: (1) patients were 18-75 years old; (2) the length of ICU stay was more than 24 hours; (3) All records of the patients were available. Data of the patients was collected by searching the electronic medical record system. Logistic regression model was formulated to create the new combined predictive indicator and the receiver operating characteristic (ROC) curve for the new predictive indicator was built. The area under the ROC curve (AUC) for both the new indicator and original ones were compared. The optimal cut-off point was obtained where the Youden index reached the maximum value. Diagnostic parameters such as sensitivity, specificity and predictive accuracy were also calculated for comparison. Finally, individual values were substituted into the equation to test the performance in predicting clinical outcomes. A total of 362 patients (218 males and 144 females) were enrolled in our study and 66 patients died. The average age was (48.3±19.3) years old. (1) For the predictive model only containing categorical covariants [including procalcitonin (PCT), lipopolysaccharide (LPS), infection, white blood cells count (WBC) and fever], increased PCT, increased WBC and fever were demonstrated to be independent risk factors for sepsis in the logistic equation. The AUC for the new combined predictive indicator was higher than that of any other indictor, including PCT, LPS, infection, WBC and fever (0.930 vs. 0.661, 0.503, 0.570, 0.837, 0.800). The optimal cut-off value for the new combined predictive indicator was 0.518. Using the new indicator to diagnose sepsis, the sensitivity, specificity and diagnostic accuracy rate were 78.00%, 93.36% and 87.47%, respectively. One patient was randomly selected, and the clinical data was substituted into the probability equation for prediction. The calculated value was 0.015, which was less than the cut-off value (0.518), indicating that the prognosis was non-sepsis at an accuracy of 87.47%. (2) For the predictive model only containing continuous covariants, the logistic model which combined acute physiology and chronic health evaluation II (APACHE II) score and sequential organ failure assessment (SOFA) score to predict in-hospital death events, both APACHE II score and SOFA score were independent risk factors for death. The AUC for the new predictive indicator was higher than that of APACHE II score and SOFA score (0.834 vs. 0.812, 0.813). The optimal cut-off value for the new combined predictive indicator in predicting in-hospital death events was 0.236, and the corresponding sensitivity, specificity and diagnostic accuracy for the combined predictive indicator were 73.12%, 76.51% and 75.70%, respectively. One patient was randomly selected, and the APACHE II score and SOFA score was substituted into the probability equation for prediction. The calculated value was 0.570, which was higher than the cut-off value (0.236), indicating that the death prognosis at an accuracy of 75.70%. The combined predictive indicator, which is formulated by logistic regression models, is superior to any single indicator in predicting sepsis or in-hospital death events.

Analysis of Binary Adherence Data in the Setting of Polypharmacy: A Comparison of Different Approaches

PubMed Central

Esserman, Denise A.; Moore, Charity G.; Roth, Mary T.

2009-01-01

Older community dwelling adults often take multiple medications for numerous chronic diseases. Non-adherence to these medications can have a large public health impact. Therefore, the measurement and modeling of medication adherence in the setting of polypharmacy is an important area of research. We apply a variety of different modeling techniques (standard linear regression; weighted linear regression; adjusted linear regression; naïve logistic regression; beta-binomial (BB) regression; generalized estimating equations (GEE)) to binary medication adherence data from a study in a North Carolina based population of older adults, where each medication an individual was taking was classified as adherent or non-adherent. In addition, through simulation we compare these different methods based on Type I error rates, bias, power, empirical 95% coverage, and goodness of fit. We find that estimation and inference using GEE is robust to a wide variety of scenarios and we recommend using this in the setting of polypharmacy when adherence is dichotomously measured for multiple medications per person. PMID:20414358

Comparison of multinomial logistic regression and logistic regression: which is more efficient in allocating land use?

NASA Astrophysics Data System (ADS)

Lin, Yingzhi; Deng, Xiangzheng; Li, Xing; Ma, Enjun

2014-12-01

Spatially explicit simulation of land use change is the basis for estimating the effects of land use and cover change on energy fluxes, ecology and the environment. At the pixel level, logistic regression is one of the most common approaches used in spatially explicit land use allocation models to determine the relationship between land use and its causal factors in driving land use change, and thereby to evaluate land use suitability. However, these models have a drawback in that they do not determine/allocate land use based on the direct relationship between land use change and its driving factors. Consequently, a multinomial logistic regression method was introduced to address this flaw, and thereby, judge the suitability of a type of land use in any given pixel in a case study area of the Jiangxi Province, China. A comparison of the two regression methods indicated that the proportion of correctly allocated pixels using multinomial logistic regression was 92.98%, which was 8.47% higher than that obtained using logistic regression. Paired t-test results also showed that pixels were more clearly distinguished by multinomial logistic regression than by logistic regression. In conclusion, multinomial logistic regression is a more efficient and accurate method for the spatial allocation of land use changes. The application of this method in future land use change studies may improve the accuracy of predicting the effects of land use and cover change on energy fluxes, ecology, and environment.

Prediction equation for estimating total daily energy requirements of special operations personnel.

PubMed

Barringer, N D; Pasiakos, S M; McClung, H L; Crombie, A P; Margolis, L M

2018-01-01

Special Operations Forces (SOF) engage in a variety of military tasks with many producing high energy expenditures, leading to undesired energy deficits and loss of body mass. Therefore, the ability to accurately estimate daily energy requirements would be useful for accurate logistical planning. Generate a predictive equation estimating energy requirements of SOF. Retrospective analysis of data collected from SOF personnel engaged in 12 different SOF training scenarios. Energy expenditure and total body water were determined using the doubly-labeled water technique. Physical activity level was determined as daily energy expenditure divided by resting metabolic rate. Physical activity level was broken into quartiles (0 = mission prep, 1 = common warrior tasks, 2 = battle drills, 3 = specialized intense activity) to generate a physical activity factor (PAF). Regression analysis was used to construct two predictive equations (Model A; body mass and PAF, Model B; fat-free mass and PAF) estimating daily energy expenditures. Average measured energy expenditure during SOF training was 4468 (range: 3700 to 6300) Kcal·d- 1 . Regression analysis revealed that physical activity level ( r  = 0.91; P  < 0.05) and body mass ( r  = 0.28; P  < 0.05; Model A), or fat-free mass (FFM; r  = 0.32; P  < 0.05; Model B) were the factors that most highly predicted energy expenditures. Predictive equations coupling PAF with body mass (Model A) and FFM (Model B), were correlated ( r  = 0.74 and r  = 0.76, respectively) and did not differ [mean ± SEM: Model A; 4463 ± 65 Kcal·d - 1 , Model B; 4462 ± 61 Kcal·d - 1 ] from DLW measured energy expenditures. By quantifying and grouping SOF training exercises into activity factors, SOF energy requirements can be predicted with reasonable accuracy and these equations used by dietetic/logistical personnel to plan appropriate feeding regimens to meet SOF nutritional requirements across their mission profile.

Recalibration of the Klales et al. (2012) method of sexing the human innominate for Mexican populations.

PubMed

Gómez-Valdés, Jorge A; Menéndez Garmendia, Antinea; García-Barzola, Lizbeth; Sánchez-Mejorada, Gabriela; Karam, Carlos; Baraybar, José Pablo; Klales, Alexandra

2017-03-01

The aim of this study was to test the accuracy of the Klales et al. (2012) equation for sex estimation in contemporary Mexican population. Our investigation was carried out on a sample of 203 left innominates of identified adult skeletons from the UNAM-Collection and the Santa María Xigui Cemetery, in Central Mexico. The Klales' original equation produces a sex bias in sex estimation against males (86-92% accuracy versus 100% accuracy in females). Based on these results, the Klales et al. (2012) method was recalibrated for a new cutt-of-point for sex estimation in contemporary Mexican populations. The results show cross-validated classification accuracy rates as high as 100% after recalibrating the original logistic regression equation. Recalibration improved classification accuracy and eliminated sex bias. This new formula will improve sex estimation for Mexican contemporary populations. © 2017 Wiley Periodicals, Inc.

Standards for Standardized Logistic Regression Coefficients

ERIC Educational Resources Information Center

Menard, Scott

2011-01-01

Standardized coefficients in logistic regression analysis have the same utility as standardized coefficients in linear regression analysis. Although there has been no consensus on the best way to construct standardized logistic regression coefficients, there is now sufficient evidence to suggest a single best approach to the construction of a…

Quantitative evaluation of infection control models in the prevention of nosocomial transmission of SARS virus to healthcare workers: implication to nosocomial viral infection control for healthcare workers.

PubMed

Yen, Muh-Yong; Lu, Yun-Ching; Huang, Pi-Hsiang; Chen, Chen-Ming; Chen, Yee-Chun; Lin, Yusen E

2010-07-01

Healthcare workers (HCWs) are at high risk of acquiring emerging infections while caring for patients, as has been shown in the recent SARS and swine flu epidemics. Using SARS as an example, we determined the effectiveness of infection control measures (ICMs) by logistic regression and structural equation modelling (SEM), a quantitative methodology that can test a hypothetical model and validates causal relationships among ICMs. Logistic regression showed that installing hand wash stations in the emergency room (p = 0.012, odds ratio = 1.07) was the only ICM significantly associated with the protection of HCWs from acquiring the SARS virus. The structural equation modelling results showed that the most important contributing factor (highest proportion of effectiveness) was installation of a fever screening station outside the emergency department (51%). Other measures included traffic control in the emergency department (19%), availability of an outbreak standard operation protocol (12%), mandatory temperature screening (9%), establishing a hand washing setup at each hospital checkpoint (3%), adding simplified isolation rooms (3%), and a standardized patient transfer protocol (3%). Installation of fever screening stations outside of the hospital and implementing traffic control in the emergency department contributed to 70% of the effectiveness in the prevention of SARS transmission. Our approach can be applied to the evaluation of control measures for other epidemic infectious diseases, including swine flu and avian flu.

A Bayesian goodness of fit test and semiparametric generalization of logistic regression with measurement data.

PubMed

Schörgendorfer, Angela; Branscum, Adam J; Hanson, Timothy E

2013-06-01

Logistic regression is a popular tool for risk analysis in medical and population health science. With continuous response data, it is common to create a dichotomous outcome for logistic regression analysis by specifying a threshold for positivity. Fitting a linear regression to the nondichotomized response variable assuming a logistic sampling model for the data has been empirically shown to yield more efficient estimates of odds ratios than ordinary logistic regression of the dichotomized endpoint. We illustrate that risk inference is not robust to departures from the parametric logistic distribution. Moreover, the model assumption of proportional odds is generally not satisfied when the condition of a logistic distribution for the data is violated, leading to biased inference from a parametric logistic analysis. We develop novel Bayesian semiparametric methodology for testing goodness of fit of parametric logistic regression with continuous measurement data. The testing procedures hold for any cutoff threshold and our approach simultaneously provides the ability to perform semiparametric risk estimation. Bayes factors are calculated using the Savage-Dickey ratio for testing the null hypothesis of logistic regression versus a semiparametric generalization. We propose a fully Bayesian and a computationally efficient empirical Bayesian approach to testing, and we present methods for semiparametric estimation of risks, relative risks, and odds ratios when parametric logistic regression fails. Theoretical results establish the consistency of the empirical Bayes test. Results from simulated data show that the proposed approach provides accurate inference irrespective of whether parametric assumptions hold or not. Evaluation of risk factors for obesity shows that different inferences are derived from an analysis of a real data set when deviations from a logistic distribution are permissible in a flexible semiparametric framework. © 2013, The International Biometric Society.

Fisher Scoring Method for Parameter Estimation of Geographically Weighted Ordinal Logistic Regression (GWOLR) Model

NASA Astrophysics Data System (ADS)

Widyaningsih, Purnami; Retno Sari Saputro, Dewi; Nugrahani Putri, Aulia

2017-06-01

GWOLR model combines geographically weighted regression (GWR) and (ordinal logistic reression) OLR models. Its parameter estimation employs maximum likelihood estimation. Such parameter estimation, however, yields difficult-to-solve system of nonlinear equations, and therefore numerical approximation approach is required. The iterative approximation approach, in general, uses Newton-Raphson (NR) method. The NR method has a disadvantage—its Hessian matrix is always the second derivatives of each iteration so it does not always produce converging results. With regard to this matter, NR model is modified by substituting its Hessian matrix into Fisher information matrix, which is termed Fisher scoring (FS). The present research seeks to determine GWOLR model parameter estimation using Fisher scoring method and apply the estimation on data of the level of vulnerability to Dengue Hemorrhagic Fever (DHF) in Semarang. The research concludes that health facilities give the greatest contribution to the probability of the number of DHF sufferers in both villages. Based on the number of the sufferers, IR category of DHF in both villages can be determined.

Socioeconomic Disparities in Telephone-Based Treatment of Tobacco Dependence

PubMed Central

Varghese, Merilyn; Stitzer, Maxine; Landes, Reid; Brackman, S. Laney; Munn, Tiffany

2014-01-01

Objectives. We examined socioeconomic disparities in tobacco dependence treatment outcomes from a free, proactive telephone counseling quitline. Methods. We delivered cognitive–behavioral treatment and nicotine patches to 6626 smokers and examined socioeconomic differences in demographic, clinical, environmental, and treatment use factors. We used logistic regressions and generalized estimating equations (GEE) to model abstinence and account for socioeconomic differences in the models. Results. The odds of achieving long-term abstinence differed by socioeconomic status (SES). In the GEE model, the odds of abstinence for the highest SES participants were 1.75 times those of the lowest SES participants. Logistic regression models revealed no treatment outcome disparity at the end of treatment, but significant disparities 3 and 6 months after treatment. Conclusions. Although quitlines often increase access to treatment for some lower SES smokers, significant socioeconomic disparities in treatment outcomes raise questions about whether current approaches are contributing to tobacco-related socioeconomic health disparities. Strategies to improve treatment outcomes for lower SES smokers might include novel methods to address multiple factors associated with socioeconomic disparities. PMID:24922165

Propensity score estimation: machine learning and classification methods as alternatives to logistic regression

PubMed Central

Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

2010-01-01

Summary Objective Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this Review was to assess machine learning alternatives to logistic regression which may accomplish the same goals but with fewer assumptions or greater accuracy. Study Design and Setting We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. Results We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (CART), and meta-classifiers (in particular, boosting). Conclusion While the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and to a lesser extent decision trees (particularly CART) appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. PMID:20630332

Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression.

PubMed

Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

2010-08-01

Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this review was to assess machine learning alternatives to logistic regression, which may accomplish the same goals but with fewer assumptions or greater accuracy. We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (classification and regression trees [CART]), and meta-classifiers (in particular, boosting). Although the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and, to a lesser extent, decision trees (particularly CART), appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. Copyright (c) 2010 Elsevier Inc. All rights reserved.

Should metacognition be measured by logistic regression?

PubMed

Rausch, Manuel; Zehetleitner, Michael

2017-03-01

Are logistic regression slopes suitable to quantify metacognitive sensitivity, i.e. the efficiency with which subjective reports differentiate between correct and incorrect task responses? We analytically show that logistic regression slopes are independent from rating criteria in one specific model of metacognition, which assumes (i) that rating decisions are based on sensory evidence generated independently of the sensory evidence used for primary task responses and (ii) that the distributions of evidence are logistic. Given a hierarchical model of metacognition, logistic regression slopes depend on rating criteria. According to all considered models, regression slopes depend on the primary task criterion. A reanalysis of previous data revealed that massive numbers of trials are required to distinguish between hierarchical and independent models with tolerable accuracy. It is argued that researchers who wish to use logistic regression as measure of metacognitive sensitivity need to control the primary task criterion and rating criteria. Copyright © 2017 Elsevier Inc. All rights reserved.

[Predicting the probability of development and progression of primary open angle glaucoma by regression modeling].

PubMed

Likhvantseva, V G; Sokolov, V A; Levanova, O N; Kovelenova, I V

2018-01-01

Prediction of the clinical course of primary open-angle glaucoma (POAG) is one of the main directions in solving the problem of vision loss prevention and stabilization of the pathological process. Simple statistical methods of correlation analysis show the extent of each risk factor's impact, but do not indicate the total impact of these factors in personalized combinations. The relationships between the risk factors is subject to correlation and regression analysis. The regression equation represents the dependence of the mathematical expectation of the resulting sign on the combination of factor signs. To develop a technique for predicting the probability of development and progression of primary open-angle glaucoma based on a personalized combination of risk factors by linear multivariate regression analysis. The study included 66 patients (23 female and 43 male; 132 eyes) with newly diagnosed primary open-angle glaucoma. The control group consisted of 14 patients (8 male and 6 female). Standard ophthalmic examination was supplemented with biochemical study of lacrimal fluid. Concentration of matrix metalloproteinase MMP-2 and MMP-9 in tear fluid in both eyes was determined using 'sandwich' enzyme-linked immunosorbent assay (ELISA) method. The study resulted in the development of regression equations and step-by-step multivariate logistic models that can help calculate the risk of development and progression of POAG. Those models are based on expert evaluation of clinical and instrumental indicators of hydrodynamic disturbances (coefficient of outflow ease - C, volume of intraocular fluid secretion - F, fluctuation of intraocular pressure), as well as personalized morphometric parameters of the retina (central retinal thickness in the macular area) and concentration of MMP-2 and MMP-9 in the tear film. The newly developed regression equations are highly informative and can be a reliable tool for studying of the influence vector and assessment of pathogenic potential of the independent risk factors in specific personalized combinations.

Comparing the Discrete and Continuous Logistic Models

ERIC Educational Resources Information Center

Gordon, Sheldon P.

2008-01-01

The solutions of the discrete logistic growth model based on a difference equation and the continuous logistic growth model based on a differential equation are compared and contrasted. The investigation is conducted using a dynamic interactive spreadsheet. (Contains 5 figures.)

London Measure of Unplanned Pregnancy: guidance for its use as an outcome measure

PubMed Central

Hall, Jennifer A; Barrett, Geraldine; Copas, Andrew; Stephenson, Judith

2017-01-01

Background The London Measure of Unplanned Pregnancy (LMUP) is a psychometrically validated measure of the degree of intention of a current or recent pregnancy. The LMUP is increasingly being used worldwide, and can be used to evaluate family planning or preconception care programs. However, beyond recommending the use of the full LMUP scale, there is no published guidance on how to use the LMUP as an outcome measure. Ordinal logistic regression has been recommended informally, but studies published to date have all used binary logistic regression and dichotomized the scale at different cut points. There is thus a need for evidence-based guidance to provide a standardized methodology for multivariate analysis and to enable comparison of results. This paper makes recommendations for the regression method for analysis of the LMUP as an outcome measure. Materials and methods Data collected from 4,244 pregnant women in Malawi were used to compare five regression methods: linear, logistic with two cut points, and ordinal logistic with either the full or grouped LMUP score. The recommendations were then tested on the original UK LMUP data. Results There were small but no important differences in the findings across the regression models. Logistic regression resulted in the largest loss of information, and assumptions were violated for the linear and ordinal logistic regression. Consequently, robust standard errors were used for linear regression and a partial proportional odds ordinal logistic regression model attempted. The latter could only be fitted for grouped LMUP score. Conclusion We recommend the linear regression model with robust standard errors to make full use of the LMUP score when analyzed as an outcome measure. Ordinal logistic regression could be considered, but a partial proportional odds model with grouped LMUP score may be required. Logistic regression is the least-favored option, due to the loss of information. For logistic regression, the cut point for un/planned pregnancy should be between nine and ten. These recommendations will standardize the analysis of LMUP data and enhance comparability of results across studies. PMID:28435343

Logistic models--an odd(s) kind of regression.

PubMed

Jupiter, Daniel C

2013-01-01

The logistic regression model bears some similarity to the multivariable linear regression with which we are familiar. However, the differences are great enough to warrant a discussion of the need for and interpretation of logistic regression. Copyright © 2013 American College of Foot and Ankle Surgeons. Published by Elsevier Inc. All rights reserved.

Parameters Estimation of Geographically Weighted Ordinal Logistic Regression (GWOLR) Model

NASA Astrophysics Data System (ADS)

Zuhdi, Shaifudin; Retno Sari Saputro, Dewi; Widyaningsih, Purnami

2017-06-01

A regression model is the representation of relationship between independent variable and dependent variable. The dependent variable has categories used in the logistic regression model to calculate odds on. The logistic regression model for dependent variable has levels in the logistics regression model is ordinal. GWOLR model is an ordinal logistic regression model influenced the geographical location of the observation site. Parameters estimation in the model needed to determine the value of a population based on sample. The purpose of this research is to parameters estimation of GWOLR model using R software. Parameter estimation uses the data amount of dengue fever patients in Semarang City. Observation units used are 144 villages in Semarang City. The results of research get GWOLR model locally for each village and to know probability of number dengue fever patient categories.

PARAMETRIC AND NON PARAMETRIC (MARS: MULTIVARIATE ADDITIVE REGRESSION SPLINES) LOGISTIC REGRESSIONS FOR PREDICTION OF A DICHOTOMOUS RESPONSE VARIABLE WITH AN EXAMPLE FOR PRESENCE/ABSENCE OF AMPHIBIANS

EPA Science Inventory

The purpose of this report is to provide a reference manual that could be used by investigators for making informed use of logistic regression using two methods (standard logistic regression and MARS). The details for analyses of relationships between a dependent binary response ...

Predicting U.S. Army Reserve Unit Manning Using Market Demographics

DTIC Science & Technology

2015-06-01

develops linear regression , classification tree, and logistic regression models to determine the ability of the location to support manning requirements... logistic regression model delivers predictive results that allow decision-makers to identify locations with a high probability of meeting unit...manning requirements. The recommendation of this thesis is that the USAR implement the logistic regression model. 14. SUBJECT TERMS U.S

Analyzing Student Learning Outcomes: Usefulness of Logistic and Cox Regression Models. IR Applications, Volume 5

ERIC Educational Resources Information Center

Chen, Chau-Kuang

2005-01-01

Logistic and Cox regression methods are practical tools used to model the relationships between certain student learning outcomes and their relevant explanatory variables. The logistic regression model fits an S-shaped curve into a binary outcome with data points of zero and one. The Cox regression model allows investigators to study the duration…

An appraisal of convergence failures in the application of logistic regression model in published manuscripts.

PubMed

Yusuf, O B; Bamgboye, E A; Afolabi, R F; Shodimu, M A

2014-09-01

Logistic regression model is widely used in health research for description and predictive purposes. Unfortunately, most researchers are sometimes not aware that the underlying principles of the techniques have failed when the algorithm for maximum likelihood does not converge. Young researchers particularly postgraduate students may not know why separation problem whether quasi or complete occurs, how to identify it and how to fix it. This study was designed to critically evaluate convergence issues in articles that employed logistic regression analysis published in an African Journal of Medicine and medical sciences between 2004 and 2013. Problems of quasi or complete separation were described and were illustrated with the National Demographic and Health Survey dataset. A critical evaluation of articles that employed logistic regression was conducted. A total of 581 articles was reviewed, of which 40 (6.9%) used binary logistic regression. Twenty-four (60.0%) stated the use of logistic regression model in the methodology while none of the articles assessed model fit. Only 3 (12.5%) properly described the procedures. Of the 40 that used the logistic regression model, the problem of convergence occurred in 6 (15.0%) of the articles. Logistic regression tends to be poorly reported in studies published between 2004 and 2013. Our findings showed that the procedure may not be well understood by researchers since very few described the process in their reports and may be totally unaware of the problem of convergence or how to deal with it.

On the analysis of Canadian Holstein dairy cow lactation curves using standard growth functions.

PubMed

López, S; France, J; Odongo, N E; McBride, R A; Kebreab, E; AlZahal, O; McBride, B W; Dijkstra, J

2015-04-01

Six classical growth functions (monomolecular, Schumacher, Gompertz, logistic, Richards, and Morgan) were fitted to individual and average (by parity) cumulative milk production curves of Canadian Holstein dairy cows. The data analyzed consisted of approximately 91,000 daily milk yield records corresponding to 122 first, 99 second, and 92 third parity individual lactation curves. The functions were fitted using nonlinear regression procedures, and their performance was assessed using goodness-of-fit statistics (coefficient of determination, residual mean squares, Akaike information criterion, and the correlation and concordance coefficients between observed and adjusted milk yields at several days in milk). Overall, all the growth functions evaluated showed an acceptable fit to the cumulative milk production curves, with the Richards equation ranking first (smallest Akaike information criterion) followed by the Morgan equation. Differences among the functions in their goodness-of-fit were enlarged when fitted to average curves by parity, where the sigmoidal functions with a variable point of inflection (Richards and Morgan) outperformed the other 4 equations. All the functions provided satisfactory predictions of milk yield (calculated from the first derivative of the functions) at different lactation stages, from early to late lactation. The Richards and Morgan equations provided the most accurate estimates of peak yield and total milk production per 305-d lactation, whereas the least accurate estimates were obtained with the logistic equation. In conclusion, classical growth functions (especially sigmoidal functions with a variable point of inflection) proved to be feasible alternatives to fit cumulative milk production curves of dairy cows, resulting in suitable statistical performance and accurate estimates of lactation traits. Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Logistic Regression: Concept and Application

ERIC Educational Resources Information Center

Cokluk, Omay

2010-01-01

The main focus of logistic regression analysis is classification of individuals in different groups. The aim of the present study is to explain basic concepts and processes of binary logistic regression analysis intended to determine the combination of independent variables which best explain the membership in certain groups called dichotomous…

Remote sensing and GIS-based landslide hazard analysis and cross-validation using multivariate logistic regression model on three test areas in Malaysia

NASA Astrophysics Data System (ADS)

Pradhan, Biswajeet

2010-05-01

This paper presents the results of the cross-validation of a multivariate logistic regression model using remote sensing data and GIS for landslide hazard analysis on the Penang, Cameron, and Selangor areas in Malaysia. Landslide locations in the study areas were identified by interpreting aerial photographs and satellite images, supported by field surveys. SPOT 5 and Landsat TM satellite imagery were used to map landcover and vegetation index, respectively. Maps of topography, soil type, lineaments and land cover were constructed from the spatial datasets. Ten factors which influence landslide occurrence, i.e., slope, aspect, curvature, distance from drainage, lithology, distance from lineaments, soil type, landcover, rainfall precipitation, and normalized difference vegetation index (ndvi), were extracted from the spatial database and the logistic regression coefficient of each factor was computed. Then the landslide hazard was analysed using the multivariate logistic regression coefficients derived not only from the data for the respective area but also using the logistic regression coefficients calculated from each of the other two areas (nine hazard maps in all) as a cross-validation of the model. For verification of the model, the results of the analyses were then compared with the field-verified landslide locations. Among the three cases of the application of logistic regression coefficient in the same study area, the case of Selangor based on the Selangor logistic regression coefficients showed the highest accuracy (94%), where as Penang based on the Penang coefficients showed the lowest accuracy (86%). Similarly, among the six cases from the cross application of logistic regression coefficient in other two areas, the case of Selangor based on logistic coefficient of Cameron showed highest (90%) prediction accuracy where as the case of Penang based on the Selangor logistic regression coefficients showed the lowest accuracy (79%). Qualitatively, the cross application model yields reasonable results which can be used for preliminary landslide hazard mapping.

An Entropy-Based Measure for Assessing Fuzziness in Logistic Regression

PubMed Central

Weiss, Brandi A.; Dardick, William

2015-01-01

This article introduces an entropy-based measure of data–model fit that can be used to assess the quality of logistic regression models. Entropy has previously been used in mixture-modeling to quantify how well individuals are classified into latent classes. The current study proposes the use of entropy for logistic regression models to quantify the quality of classification and separation of group membership. Entropy complements preexisting measures of data–model fit and provides unique information not contained in other measures. Hypothetical data scenarios, an applied example, and Monte Carlo simulation results are used to demonstrate the application of entropy in logistic regression. Entropy should be used in conjunction with other measures of data–model fit to assess how well logistic regression models classify cases into observed categories. PMID:29795897

Logistic regression applied to natural hazards: rare event logistic regression with replications

NASA Astrophysics Data System (ADS)

Guns, M.; Vanacker, V.

2012-06-01

Statistical analysis of natural hazards needs particular attention, as most of these phenomena are rare events. This study shows that the ordinary rare event logistic regression, as it is now commonly used in geomorphologic studies, does not always lead to a robust detection of controlling factors, as the results can be strongly sample-dependent. In this paper, we introduce some concepts of Monte Carlo simulations in rare event logistic regression. This technique, so-called rare event logistic regression with replications, combines the strength of probabilistic and statistical methods, and allows overcoming some of the limitations of previous developments through robust variable selection. This technique was here developed for the analyses of landslide controlling factors, but the concept is widely applicable for statistical analyses of natural hazards.

Large unbalanced credit scoring using Lasso-logistic regression ensemble.

PubMed

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data.

An Entropy-Based Measure for Assessing Fuzziness in Logistic Regression.

PubMed

Weiss, Brandi A; Dardick, William

2016-12-01

This article introduces an entropy-based measure of data-model fit that can be used to assess the quality of logistic regression models. Entropy has previously been used in mixture-modeling to quantify how well individuals are classified into latent classes. The current study proposes the use of entropy for logistic regression models to quantify the quality of classification and separation of group membership. Entropy complements preexisting measures of data-model fit and provides unique information not contained in other measures. Hypothetical data scenarios, an applied example, and Monte Carlo simulation results are used to demonstrate the application of entropy in logistic regression. Entropy should be used in conjunction with other measures of data-model fit to assess how well logistic regression models classify cases into observed categories.

Does the Aristotle Score predict outcome in congenital heart surgery?

PubMed

Kang, Nicholas; Tsang, Victor T; Elliott, Martin J; de Leval, Marc R; Cole, Timothy J

2006-06-01

The Aristotle Score has been proposed as a measure of 'complexity' in congenital heart surgery, and a tool for comparing performance amongst different centres. To date, however, it remains unvalidated. We examined whether the Basic Aristotle Score was a useful predictor of mortality following open-heart surgery, and compared it to the Risk Adjustment in Congenital Heart Surgery (RACHS-1) system. We also examined the ability of the Aristotle Score to measure performance. The Basic Aristotle Score and RACHS-1 risk categories were assigned retrospectively to 1085 operations involving cardiopulmonary bypass in children less than 18 years of age. Multiple logistic regression analysis was used to determine the significance of the Aristotle Score and RACHS-1 category as independent predictors of in-hospital mortality. Operative performance was calculated using the Aristotle equation: performance = complexity x survival. Multiple logistic regression identified RACHS-1 category to be a powerful predictor of mortality (Wald 17.7, p < 0.0001), whereas Aristotle Score was only weakly associated with mortality (Wald 4.8, p = 0.03). Age at operation and bypass time were also highly significant predictors of postoperative death (Wald 13.7 and 33.8, respectively, p < 0.0001 for both). Operative performance was measured at 7.52 units. The Basic Aristotle Score was only weakly associated with postoperative mortality in this series. Operative performance appeared to be inflated by the fact that the overall complexity of cases was relatively high in this series. An alternative equation (performance = complexity/mortality) is proposed as a fairer and more logical method of risk-adjustment.

Ultrasound predictors of placental invasion: the Placenta Accreta Index.

PubMed

Rac, Martha W F; Dashe, Jodi S; Wells, C Edward; Moschos, Elysia; McIntire, Donald D; Twickler, Diane M

2015-03-01

We sought to apply a standardized evaluation of ultrasound parameters for the prediction of placental invasion in a high-risk population. This was a retrospective review of gravidas with ≥1 prior cesarean delivery who received an ultrasound diagnosis of placenta previa or low-lying placenta in the third trimester at our institution from 1997 through 2011. Sonographic images were reviewed by an investigator blinded to pregnancy outcome and sonography reports. Parameters assessed included loss of retroplacental clear zone, irregularity and width of uterine-bladder interface, smallest myometrial thickness, presence of lacunar spaces, and bridging vessels. Diagnosis of placental invasion was based on histologic confirmation. Statistical analyses were performed using linear logistic regression and multiparametric analyses to generate a predictive equation evaluated using a receiver operating characteristic curve. Of 184 gravidas who met inclusion criteria, 54 (29%) had invasion confirmed on hysterectomy specimen. All sonographic parameters were associated with placental invasion (P < .001). Constructing a receiver operating characteristic curve, the combination of smallest sagittal myometrial thickness, lacunae, and bridging vessels, in addition to number of cesarean deliveries and placental location, yielded an area under the curve of 0.87 (95% confidence interval, 0.80-0.95). Using logistic regression, a predictive equation was generated, termed the "Placenta Accreta Index." Each parameter was weighted to create a 9-point scale in which a score of 0-9 provided a probability of invasion that ranged from 2-96%, respectively. Assignment of the Placenta Accreta Index may be helpful in predicting individual patient risk for morbidly adherent placenta. Copyright © 2015 Elsevier Inc. All rights reserved.

Forecasting Lightning at Kennedy Space Center/Cape Canaveral Air Force Station, Florida

NASA Technical Reports Server (NTRS)

Lambert, Winfred; Wheeler, Mark; Roeder, William

2005-01-01

The Applied Meteorology Unit (AMU) developed a set of statistical forecast equations that provide a probability of lightning occurrence on Kennedy Space Center (KSC) I Cape Canaveral Air Force Station (CCAFS) for the day during the warm season (May September). The 45th Weather Squadron (45 WS) forecasters at CCAFS in Florida include a probability of lightning occurrence in their daily 24-hour and weekly planning forecasts, which are briefed at 1100 UTC (0700 EDT). This information is used for general scheduling of operations at CCAFS and KSC. Forecasters at the Spaceflight Meteorology Group also make thunderstorm forecasts for the KSC/CCAFS area during Shuttle flight operations. Much of the current lightning probability forecast at both groups is based on a subjective analysis of model and observational data. The objective tool currently available is the Neumann-Pfeffer Thunderstorm Index (NPTI, Neumann 1971), developed specifically for the KSCICCAFS area over 30 years ago. However, recent studies have shown that 1-day persistence provides a better forecast than the NPTI, indicating that the NPTI needed to be upgraded or replaced. Because they require a tool that provides a reliable estimate of the daily thunderstorm probability forecast, the 45 WS forecasters requested that the AMU develop a new lightning probability forecast tool using recent data and more sophisticated techniques now possible through more computing power than that available over 30 years ago. The equation development incorporated results from two research projects that investigated causes of lightning occurrence near KSCICCAFS and over the Florida peninsula. One proved that logistic regression outperformed the linear regression method used in NPTI, even when the same predictors were used. The other study found relationships between large scale flow regimes and spatial lightning distributions over Florida. Lightning, probabilities based on these flow regimes were used as candidate predictors in the equation development. Fifteen years (1 989-2003) of warm season data were used to develop the forecast equations. The data sources included a local network of cloud-to-ground lightning sensors called the Cloud-to-Ground Lightning Surveillance System (CGLSS), 1200 UTC Florida synoptic soundings, and the 1000 UTC CCAFS sounding. Data from CGLSS were used to determine lightning occurrence for each day. The 1200 UTC soundings were used to calculate the synoptic-scale flow regimes and the 1000 UTC soundings were used to calculate local stability parameters, which were used as candidate predictors of lightning occurrence. Five logistic regression forecast equations were created through careful selection and elimination of the candidate predictors. The resulting equations contain five to six predictors each. Results from four performance tests indicated that the equations showed an increase in skill over several standard forecasting methods, good reliability, an ability to distinguish between non-lightning and lightning days, and good accuracy measures and skill scores. Given the overall good performance the 45 WS requested that the equations be transitioned to operations and added to the current set of tools used to determine the daily lightning probability of occurrence.

aLicante sUrgical Community Emergencies New Tool for the enUmeration of Morbidities: a simplified auditing tool for community-acquired gastrointestinal surgical emergencies.

PubMed

Villodre, Celia; Rebasa, Pere; Estrada, José Luís; Zaragoza, Carmen; Zapater, Pedro; Mena, Luís; Lluís, Félix

2016-11-01

In a previous study, we found that Physiological and Operative Severity Score for the enUmeration of Mortality and Morbidity (POSSUM) overpredicts morbidity risk in emergency gastrointestinal surgery. Our aim was to find a POSSUM equation adjustment. A prospective observational study was performed on 2,361 patients presenting with a community-acquired gastrointestinal surgical emergency. The first 1,000 surgeries constituted the development cohort, the second 1,000 events were the first validation intramural cohort, and the remaining 361 cases belonged to a second validation extramural cohort. (1) A modified POSSUM equation was obtained. (2) Logistic regression was used to yield a statistically significant equation that included age, hemoglobin, white cell count, sodium and operative severity. (3) A chi-square automatic interaction detector decision tree analysis yielded a statistically significant equation with 4 variables, namely cardiac failure, sodium, operative severity, and peritoneal soiling. A modified POSSUM equation and a simplified scoring system (aLicante sUrgical Community Emergencies New Tool for the enUmeration of Morbidities [LUCENTUM]) are described. Both tools significantly improve prediction of surgical morbidity in community-acquired gastrointestinal surgical emergencies. Copyright © 2016 Elsevier Inc. All rights reserved.

Power and Sample Size Calculations for Logistic Regression Tests for Differential Item Functioning

ERIC Educational Resources Information Center

Li, Zhushan

2014-01-01

Logistic regression is a popular method for detecting uniform and nonuniform differential item functioning (DIF) effects. Theoretical formulas for the power and sample size calculations are derived for likelihood ratio tests and Wald tests based on the asymptotic distribution of the maximum likelihood estimators for the logistic regression model.…

A Methodology for Generating Placement Rules that Utilizes Logistic Regression

ERIC Educational Resources Information Center

Wurtz, Keith

2008-01-01

The purpose of this article is to provide the necessary tools for institutional researchers to conduct a logistic regression analysis and interpret the results. Aspects of the logistic regression procedure that are necessary to evaluate models are presented and discussed with an emphasis on cutoff values and choosing the appropriate number of…

Comparison of standard maximum likelihood classification and polytomous logistic regression used in remote sensing

Treesearch

John Hogland; Nedret Billor; Nathaniel Anderson

2013-01-01

Discriminant analysis, referred to as maximum likelihood classification within popular remote sensing software packages, is a common supervised technique used by analysts. Polytomous logistic regression (PLR), also referred to as multinomial logistic regression, is an alternative classification approach that is less restrictive, more flexible, and easy to interpret. To...

Validation of use of the International Consultation on Incontinence Questionnaire-Urinary Incontinence-Short Form (ICIQ-UI-SF) for impairment rating: a transversal retrospective study of 120 patients.

PubMed

Timmermans, Luc; Falez, Freddy; Mélot, Christian; Wespes, Eric

2013-09-01

A urinary incontinence impairment rating must be a highly accurate, non-invasive exploration of the condition using International Classification of Functioning (ICF)-based assessment tools. The objective of this study was to identify the best evaluation test and to determine an impairment rating model of urinary incontinence. In performing a cross-sectional study comparing successive urodynamic tests using both the International Consultation on Incontinence Questionnaire-Urinary Incontinence-Short Form (ICIQ-UI-SF) and the 1-hr pad-weighing test in 120 patients, we performed statistical likelihood ratio analysis and used logistic regression to calculate the probability of urodynamic incontinence using the most significant independent predictors. Subsequently, we created a template that was based on the significant predictors and the probability of urodynamic incontinence. The mean ICIQ-UI-SF score was 13.5 ± 4.6, and the median pad test value was 8 g. The discrimination statistic (receiver operating characteristic) described how well the urodynamic observations matched the ICIQ-UI-SF scores (under curve area (UDA):0.689) and the pad test data (UDA: 0.693). Using logistic regression analysis, we demonstrated that the best independent predictors of urodynamic incontinence were the patient's age and the ICIQ-UI-SF score. The logistic regression model permitted us to construct an equation to determine the probability of urodynamic incontinence. Using these tools, we created a template to generate a probability index of urodynamic urinary incontinence. Using this probability index, relative to the patient and to the maximum impairment of the whole person (MIWP) relative to urinary incontinence, we were able to calculate a patient's permanent impairment. Copyright © 2012 Wiley Periodicals, Inc.

Integration of logistic regression and multicriteria land evaluation to simulation establishment of sustainable paddy field zone in Indramayu Regency, West Java Province, Indonesia

NASA Astrophysics Data System (ADS)

Nahib, Irmadi; Suryanta, Jaka; Niedyawati; Kardono, Priyadi; Turmudi; Lestari, Sri; Windiastuti, Rizka

2018-05-01

Ministry of Agriculture have targeted production of 1.718 million tons of dry grain harvest during period of 2016-2021 to achieve food self-sufficiency, through optimization of special commodities including paddy, soybean and corn. This research was conducted to develop a sustainable paddy field zone delineation model using logistic regression and multicriteria land evaluation in Indramayu Regency. A model was built on the characteristics of local function conversion by considering the concept of sustainable development. Spatial data overlay was constructed using available data, and then this model was built upon the occurrence of paddy field between 1998 and 2015. Equation for the model of paddy field changes obtained was: logit (paddy field conversion) = - 2.3048 + 0.0032*X1 – 0.0027*X2 + 0.0081*X3 + 0.0025*X4 + 0.0026*X5 + 0.0128*X6 – 0.0093*X7 + 0.0032*X8 + 0.0071*X9 – 0.0046*X10 where X1 to X10 were variables that determine the occurrence of changes in paddy fields, with a result value of Relative Operating Characteristics (ROC) of 0.8262. The weakest variable in influencing the change of paddy field function was X7 (paddy field price), while the most influential factor was X1 (distance from river). Result of the logistic regression was used as a weight for multicriteria land evaluation, which recommended three scenarios of paddy fields protection policy: standard, protective, and permissive. The result of this modelling, the priority paddy fields for protected scenario were obtained, as well as the buffer zones for the surrounding paddy fields.

Development of an Algorithm for Stroke Prediction: A National Health Insurance Database Study in Korea.

PubMed

Min, Seung Nam; Park, Se Jin; Kim, Dong Joon; Subramaniyam, Murali; Lee, Kyung-Sun

2018-01-01

Stroke is the second leading cause of death worldwide and remains an important health burden both for the individuals and for the national healthcare systems. Potentially modifiable risk factors for stroke include hypertension, cardiac disease, diabetes, and dysregulation of glucose metabolism, atrial fibrillation, and lifestyle factors. We aimed to derive a model equation for developing a stroke pre-diagnosis algorithm with the potentially modifiable risk factors. We used logistic regression for model derivation, together with data from the database of the Korea National Health Insurance Service (NHIS). We reviewed the NHIS records of 500,000 enrollees. For the regression analysis, data regarding 367 stroke patients were selected. The control group consisted of 500 patients followed up for 2 consecutive years and with no history of stroke. We developed a logistic regression model based on information regarding several well-known modifiable risk factors. The developed model could correctly discriminate between normal subjects and stroke patients in 65% of cases. The model developed in the present study can be applied in the clinical setting to estimate the probability of stroke in a year and thus improve the stroke prevention strategies in high-risk patients. The approach used to develop the stroke prevention algorithm can be applied for developing similar models for the pre-diagnosis of other diseases. © 2018 S. Karger AG, Basel.

Large Unbalanced Credit Scoring Using Lasso-Logistic Regression Ensemble

PubMed Central

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data. PMID:25706988

Logistic Achievement Test Scaling and Equating with Fixed versus Estimated Lower Asymptotes.

ERIC Educational Resources Information Center

Phillips, S. E.

This study compared the lower asymptotes estimated by the maximum likelihood procedures of the LOGIST computer program with those obtained via application of the Norton methodology. The study also compared the equating results from the three-parameter logistic model with those obtained from the equipercentile, Rasch, and conditional…

Sex discrimination from the acetabulum in a twentieth-century skeletal sample from France using digital photogrammetry.

PubMed

Macaluso, P J

2011-02-01

Digital photogrammetric methods were used to collect diameter, area, and perimeter data of the acetabulum for a twentieth-century skeletal sample from France (Georges Olivier Collection, Musée de l'Homme, Paris) consisting of 46 males and 36 females. The measurements were then subjected to both discriminant function and logistic regression analyses in order to develop osteometric standards for sex assessment. Univariate discriminant functions and logistic regression equations yielded overall correct classification accuracy rates for both the left and the right acetabula ranging from 84.1% to 89.6%. The multivariate models developed in this study did not provide increased accuracy over those using only a single variable. Classification sex bias ratios ranged between 1.1% and 7.3% for the majority of models. The results of this study, therefore, demonstrate that metric analysis of acetabular size provides a highly accurate, and easily replicable, method of discriminating sex in this documented skeletal collection. The results further suggest that the addition of area and perimeter data derived from digital images may provide a more effective method of sex assessment than that offered by traditional linear measurements alone. Copyright © 2010 Elsevier GmbH. All rights reserved.

Modeling the pressure inactivation of Escherichia coli and Salmonella typhimurium in sapote mamey ( Pouteria sapota (Jacq.) H.E. Moore & Stearn) pulp.

PubMed

Saucedo-Reyes, Daniela; Carrillo-Salazar, José A; Román-Padilla, Lizbeth; Saucedo-Veloz, Crescenciano; Reyes-Santamaría, María I; Ramírez-Gilly, Mariana; Tecante, Alberto

2018-03-01

High hydrostatic pressure inactivation kinetics of Escherichia coli ATCC 25922 and Salmonella enterica subsp. enterica serovar Typhimurium ATCC 14028 ( S. typhimurium) in a low acid mamey pulp at four pressure levels (300, 350, 400, and 450 MPa), different exposure times (0-8 min), and temperature of 25 ± 2℃ were obtained. Survival curves showed deviations from linearity in the form of a tail (upward concavity). The primary models tested were the Weibull model, the modified Gompertz equation, and the biphasic model. The Weibull model gave the best goodness of fit ( R 2 adj  > 0.956, root mean square error < 0.290) in the modeling and the lowest Akaike information criterion value. Exponential-logistic and exponential decay models, and Bigelow-type and an empirical models for b'( P) and n( P) parameters, respectively, were tested as alternative secondary models. The process validation considered the two- and one-step nonlinear regressions for making predictions of the survival fraction; both regression types provided an adequate goodness of fit and the one-step nonlinear regression clearly reduced fitting errors. The best candidate model according to the Akaike theory information, with better accuracy and more reliable predictions was the Weibull model integrated by the exponential-logistic and exponential decay secondary models as a function of time and pressure (two-step procedure) or incorporated as one equation (one-step procedure). Both mathematical expressions were used to determine the t d parameter, where the desired reductions ( 5D) (considering d = 5 ( t 5 ) as the criterion of 5 Log 10 reduction (5 D)) in both microorganisms are attainable at 400 MPa for 5.487 ± 0.488 or 5.950 ± 0.329 min, respectively, for the one- or two-step nonlinear procedure.

R programming for parameters estimation of geographically weighted ordinal logistic regression (GWOLR) model based on Newton Raphson

NASA Astrophysics Data System (ADS)

Zuhdi, Shaifudin; Saputro, Dewi Retno Sari

2017-03-01

GWOLR model used for represent relationship between dependent variable has categories and scale of category is ordinal with independent variable influenced the geographical location of the observation site. Parameters estimation of GWOLR model use maximum likelihood provide system of nonlinear equations and hard to be found the result in analytic resolution. By finishing it, it means determine the maximum completion, this thing associated with optimizing problem. The completion nonlinear system of equations optimize use numerical approximation, which one is Newton Raphson method. The purpose of this research is to make iteration algorithm Newton Raphson and program using R software to estimate GWOLR model. Based on the research obtained that program in R can be used to estimate the parameters of GWOLR model by forming a syntax program with command "while".

Psychotropic substance abuse among adolescents: a structural equation model on risk and protective factors.

PubMed

Rumpold, Gerhard; Klingseis, Michael; Dornauer, Kurt; Kopp, Martin; Doering, Stephan; Höfer, Stefan; Mumelter, Birgit; Schüssler, Gerhard

2006-01-01

The use of psychotropic substances in adolescents represents a serious public health problem. In this study a representative sample of 485 Austrian students between 14 and 18 years of age were investigated with a semistructured interview about substance-related issues and completed the general health questionnaire. The following rates of regular psychotropic substance use were found: cigarettes 41.4%, alcohol 44.5%, cannabis 10.1%, and other illicit substances 3%. Logistic regression analyses and structural equation modeling revealed the following major risk factors for substance use: peer pressure, negative family atmosphere, school difficulties, and psychopathology. Knowledge about substance use acted as a protective factor. Prevention of adolescent substance use and misuse should aim at these different targets. Information about coping with peer pressure may be a particularly promising route of intervention.

Combination of c-reactive protein and squamous cell carcinoma antigen in predicting postoperative prognosis for patients with squamous cell carcinoma of the esophagus.

PubMed

Feng, Ji-Feng; Chen, Sheng; Yang, Xun

2017-09-08

We initially proposed a useful and novel prognostic model, named CCS [Combination of c-reactive protein (CRP) and squamous cell carcinoma antigen (SCC)], for predicting the postoperative survival in patients with esophageal squamous cell carcinoma (ESCC). Two hundred and fifty-two patients with resectable ESCC were included in this retrospective study. A logistic regression was performed and yielded a logistic equation. The CCS was calculated by the combined CRP and SCC. The optimal cut-off value for CCS was evaluated by X-tile program. Univariate and multivariate analyses were used to evaluate the predictive factors. In addition, a novel nomogram model was also performed to predict the prognosis for patients with ESCC. In the current study, CCS was calculated as CRP+6.33 SCC according to the logistic equation. The optimal cut-off value was 15.8 for CCS according to the X-tile program. Kaplan-Meier analyses demonstrated that high CCS group had a significantly poor 5-year cancer-specific survival (CSS) than low CCS group (10.3% vs. 47.3%, P <0.001). According to multivariate analyses, CCS ( P =0.004), but not CRP ( P =0.466) or SCC ( P =0.926), was an independent prognostic factor. A nomogram could be more accuracy for CSS (Harrell's c-index: 0.70). The CCS is a usefull and independent predictive factor in patients with ESCC.

Effect of Initial Conditions on Reproducibility of Scientific Research

PubMed Central

Djulbegovic, Benjamin; Hozo, Iztok

2014-01-01

Background: It is estimated that about half of currently published research cannot be reproduced. Many reasons have been offered as explanations for failure to reproduce scientific research findings- from fraud to the issues related to design, conduct, analysis, or publishing scientific research. We also postulate a sensitive dependency on initial conditions by which small changes can result in the large differences in the research findings when attempted to be reproduced at later times. Methods: We employed a simple logistic regression equation to model the effect of covariates on the initial study findings. We then fed the input from the logistic equation into a logistic map function to model stability of the results in repeated experiments over time. We illustrate the approach by modeling effects of different factors on the choice of correct treatment. Results: We found that reproducibility of the study findings depended both on the initial values of all independent variables and the rate of change in the baseline conditions, the latter being more important. When the changes in the baseline conditions vary by about 3.5 to about 4 in between experiments, no research findings could be reproduced. However, when the rate of change between the experiments is ≤2.5 the results become highly predictable between the experiments. Conclusions: Many results cannot be reproduced because of the changes in the initial conditions between the experiments. Better control of the baseline conditions in-between the experiments may help improve reproducibility of scientific findings. PMID:25132705

Effect of initial conditions on reproducibility of scientific research.

PubMed

Djulbegovic, Benjamin; Hozo, Iztok

2014-06-01

It is estimated that about half of currently published research cannot be reproduced. Many reasons have been offered as explanations for failure to reproduce scientific research findings- from fraud to the issues related to design, conduct, analysis, or publishing scientific research. We also postulate a sensitive dependency on initial conditions by which small changes can result in the large differences in the research findings when attempted to be reproduced at later times. We employed a simple logistic regression equation to model the effect of covariates on the initial study findings. We then fed the input from the logistic equation into a logistic map function to model stability of the results in repeated experiments over time. We illustrate the approach by modeling effects of different factors on the choice of correct treatment. We found that reproducibility of the study findings depended both on the initial values of all independent variables and the rate of change in the baseline conditions, the latter being more important. When the changes in the baseline conditions vary by about 3.5 to about 4 in between experiments, no research findings could be reproduced. However, when the rate of change between the experiments is ≤2.5 the results become highly predictable between the experiments. Many results cannot be reproduced because of the changes in the initial conditions between the experiments. Better control of the baseline conditions in-between the experiments may help improve reproducibility of scientific findings.

An Entropy-Based Measure for Assessing Fuzziness in Logistic Regression

ERIC Educational Resources Information Center

Weiss, Brandi A.; Dardick, William

2016-01-01

This article introduces an entropy-based measure of data-model fit that can be used to assess the quality of logistic regression models. Entropy has previously been used in mixture-modeling to quantify how well individuals are classified into latent classes. The current study proposes the use of entropy for logistic regression models to quantify…

What Are the Odds of that? A Primer on Understanding Logistic Regression

ERIC Educational Resources Information Center

Huang, Francis L.; Moon, Tonya R.

2013-01-01

The purpose of this Methodological Brief is to present a brief primer on logistic regression, a commonly used technique when modeling dichotomous outcomes. Using data from the National Education Longitudinal Study of 1988 (NELS:88), logistic regression techniques were used to investigate student-level variables in eighth grade (i.e., enrolled in a…

Efficacy of "Dimodent" sex predictive equation assessed in an Indian population.

PubMed

Bharti, A; Angadi, P V; Kale, A D; Hallikerimath, S R

2011-07-01

Teeth are considered as a useful adjunct for sex assessment and may play an important role in constructing a post-mortem profile. The Dimodent method is based on the high degree of sex discrimination obtained with the mandibular canine and the high correlation coefficients between mandibular canine and lateral incisor mesiodistal (MD) and buccolingual (BL) dimensions. This has been evaluated in the French and Lebanese, but no study exists on its efficacy in Indians. Here, we have applied the 'Dimodent' equation on an Indian sample (100 males, 100 females; age range of 19-27yrs). Additionally, a population-specific Dimodent equation was derived using logistic regression analysis and applied to our sample. Also, the sex determination potential of MD and BL measurements of mandibular lateral incisors and canines, individually, was assessed. We found a poor sex assessment accuracy using the Dimodent equation of Fronty (34.5%) in our Indian sample, but the populationspecific Dimodent equation gave a better accuracy (72%).Thus, it appears that sexual dimorphism in teeth is population-specific; consequently the Dimodent equation has to be derived individually in different populations for use in sex assessment. The mesiodistal measurement of the mandibular canine alone gave a marginally higher accuracy (72.5%); therefore, we suggest the use of mandibular canines alone rather than the Dimodent method.

Sourcing for Parameter Estimation and Study of Logistic Differential Equation

ERIC Educational Resources Information Center

Winkel, Brian J.

2012-01-01

This article offers modelling opportunities in which the phenomena of the spread of disease, perception of changing mass, growth of technology, and dissemination of information can be described by one differential equation--the logistic differential equation. It presents two simulation activities for students to generate real data, as well as…

On the Usefulness of a Multilevel Logistic Regression Approach to Person-Fit Analysis

ERIC Educational Resources Information Center

Conijn, Judith M.; Emons, Wilco H. M.; van Assen, Marcel A. L. M.; Sijtsma, Klaas

2011-01-01

The logistic person response function (PRF) models the probability of a correct response as a function of the item locations. Reise (2000) proposed to use the slope parameter of the logistic PRF as a person-fit measure. He reformulated the logistic PRF model as a multilevel logistic regression model and estimated the PRF parameters from this…

Inability to access addiction treatment among street-involved youth in a Canadian setting.

PubMed

Phillips, Mark; DeBeck, Kora; Desjarlais, Timothy; Morrison, Tracey; Feng, Cindy; Kerr, Thomas; Wood, Evan

2014-08-01

From Sept 2005 to May 2012, 1015 street-involved youth were enrolled into the At-Risk Youth Study, a prospective cohort of youth aged 14-26 who use illicit drugs in Vancouver, Canada. Data were collected through semiannual interviewer administered questionnaires. Generalized estimating equation logistic regression was used to identify factors independently associated with being unable to access addiction treatment. The enclosed manuscript notes the implications and limitations of this study, as well as possible directions for future research. This study was funded by the US National Institutes of Health (NIH) and Canadian Institutes of Health (CIHR).

Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches.

PubMed

Stylianou, Neophytos; Akbarov, Artur; Kontopantelis, Evangelos; Buchan, Iain; Dunn, Ken W

2015-08-01

Predicting mortality from burn injury has traditionally employed logistic regression models. Alternative machine learning methods have been introduced in some areas of clinical prediction as the necessary software and computational facilities have become accessible. Here we compare logistic regression and machine learning predictions of mortality from burn. An established logistic mortality model was compared to machine learning methods (artificial neural network, support vector machine, random forests and naïve Bayes) using a population-based (England & Wales) case-cohort registry. Predictive evaluation used: area under the receiver operating characteristic curve; sensitivity; specificity; positive predictive value and Youden's index. All methods had comparable discriminatory abilities, similar sensitivities, specificities and positive predictive values. Although some machine learning methods performed marginally better than logistic regression the differences were seldom statistically significant and clinically insubstantial. Random forests were marginally better for high positive predictive value and reasonable sensitivity. Neural networks yielded slightly better prediction overall. Logistic regression gives an optimal mix of performance and interpretability. The established logistic regression model of burn mortality performs well against more complex alternatives. Clinical prediction with a small set of strong, stable, independent predictors is unlikely to gain much from machine learning outside specialist research contexts. Copyright © 2015 Elsevier Ltd and ISBI. All rights reserved.

Bias in logistic regression due to imperfect diagnostic test results and practical correction approaches.

PubMed

Valle, Denis; Lima, Joanna M Tucker; Millar, Justin; Amratia, Punam; Haque, Ubydul

2015-11-04

Logistic regression is a statistical model widely used in cross-sectional and cohort studies to identify and quantify the effects of potential disease risk factors. However, the impact of imperfect tests on adjusted odds ratios (and thus on the identification of risk factors) is under-appreciated. The purpose of this article is to draw attention to the problem associated with modelling imperfect diagnostic tests, and propose simple Bayesian models to adequately address this issue. A systematic literature review was conducted to determine the proportion of malaria studies that appropriately accounted for false-negatives/false-positives in a logistic regression setting. Inference from the standard logistic regression was also compared with that from three proposed Bayesian models using simulations and malaria data from the western Brazilian Amazon. A systematic literature review suggests that malaria epidemiologists are largely unaware of the problem of using logistic regression to model imperfect diagnostic test results. Simulation results reveal that statistical inference can be substantially improved when using the proposed Bayesian models versus the standard logistic regression. Finally, analysis of original malaria data with one of the proposed Bayesian models reveals that microscopy sensitivity is strongly influenced by how long people have lived in the study region, and an important risk factor (i.e., participation in forest extractivism) is identified that would have been missed by standard logistic regression. Given the numerous diagnostic methods employed by malaria researchers and the ubiquitous use of logistic regression to model the results of these diagnostic tests, this paper provides critical guidelines to improve data analysis practice in the presence of misclassification error. Easy-to-use code that can be readily adapted to WinBUGS is provided, enabling straightforward implementation of the proposed Bayesian models.

Positive solutions to logistic type equations with harvesting

NASA Astrophysics Data System (ADS)

Girão, Pedro; Tehrani, Hossein

We use comparison principles, variational arguments and a truncation method to obtain positive solutions to logistic type equations with harvesting both in R and in a bounded domain Ω⊂R, with N⩾3, when the carrying capacity of the environment is not constant. By relaxing the growth assumption on the coefficients of the differential equation we derive a new equation which is easily solved. The solution of this new equation is then used to produce a positive solution of our original problem.

Logistic regression for risk factor modelling in stuttering research.

PubMed

Reed, Phil; Wu, Yaqionq

2013-06-01

To outline the uses of logistic regression and other statistical methods for risk factor analysis in the context of research on stuttering. The principles underlying the application of a logistic regression are illustrated, and the types of questions to which such a technique has been applied in the stuttering field are outlined. The assumptions and limitations of the technique are discussed with respect to existing stuttering research, and with respect to formulating appropriate research strategies to accommodate these considerations. Finally, some alternatives to the approach are briefly discussed. The way the statistical procedures are employed are demonstrated with some hypothetical data. Research into several practical issues concerning stuttering could benefit if risk factor modelling were used. Important examples are early diagnosis, prognosis (whether a child will recover or persist) and assessment of treatment outcome. After reading this article you will: (a) Summarize the situations in which logistic regression can be applied to a range of issues about stuttering; (b) Follow the steps in performing a logistic regression analysis; (c) Describe the assumptions of the logistic regression technique and the precautions that need to be checked when it is employed; (d) Be able to summarize its advantages over other techniques like estimation of group differences and simple regression. Copyright © 2012 Elsevier Inc. All rights reserved.

Dynamic Dimensionality Selection for Bayesian Classifier Ensembles

DTIC Science & Technology

2015-03-19

learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very cometitive to Logistic Regression but much more...classifier, Generative learning, Discriminative learning, Naïve Bayes, Feature selection, Logistic regression , higher order attribute independence 16...discriminative learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very cometitive to Logistic Regression but

A review of logistic regression models used to predict post-fire tree mortality of western North American conifers

Treesearch

Travis Woolley; David C. Shaw; Lisa M. Ganio; Stephen Fitzgerald

2012-01-01

Logistic regression models used to predict tree mortality are critical to post-fire management, planning prescribed bums and understanding disturbance ecology. We review literature concerning post-fire mortality prediction using logistic regression models for coniferous tree species in the western USA. We include synthesis and review of: methods to develop, evaluate...

Preserving Institutional Privacy in Distributed binary Logistic Regression.

PubMed

Wu, Yuan; Jiang, Xiaoqian; Ohno-Machado, Lucila

2012-01-01

Privacy is becoming a major concern when sharing biomedical data across institutions. Although methods for protecting privacy of individual patients have been proposed, it is not clear how to protect the institutional privacy, which is many times a critical concern of data custodians. Built upon our previous work, Grid Binary LOgistic REgression (GLORE)1, we developed an Institutional Privacy-preserving Distributed binary Logistic Regression model (IPDLR) that considers both individual and institutional privacy for building a logistic regression model in a distributed manner. We tested our method using both simulated and clinical data, showing how it is possible to protect the privacy of individuals and of institutions using a distributed strategy.

Covariate Imbalance and Adjustment for Logistic Regression Analysis of Clinical Trial Data

PubMed Central

Ciolino, Jody D.; Martin, Reneé H.; Zhao, Wenle; Jauch, Edward C.; Hill, Michael D.; Palesch, Yuko Y.

2014-01-01

In logistic regression analysis for binary clinical trial data, adjusted treatment effect estimates are often not equivalent to unadjusted estimates in the presence of influential covariates. This paper uses simulation to quantify the benefit of covariate adjustment in logistic regression. However, International Conference on Harmonization guidelines suggest that covariate adjustment be pre-specified. Unplanned adjusted analyses should be considered secondary. Results suggest that that if adjustment is not possible or unplanned in a logistic setting, balance in continuous covariates can alleviate some (but never all) of the shortcomings of unadjusted analyses. The case of log binomial regression is also explored. PMID:24138438

Differentially private distributed logistic regression using private and public data.

PubMed

Ji, Zhanglong; Jiang, Xiaoqian; Wang, Shuang; Xiong, Li; Ohno-Machado, Lucila

2014-01-01

Privacy protecting is an important issue in medical informatics and differential privacy is a state-of-the-art framework for data privacy research. Differential privacy offers provable privacy against attackers who have auxiliary information, and can be applied to data mining models (for example, logistic regression). However, differentially private methods sometimes introduce too much noise and make outputs less useful. Given available public data in medical research (e.g. from patients who sign open-consent agreements), we can design algorithms that use both public and private data sets to decrease the amount of noise that is introduced. In this paper, we modify the update step in Newton-Raphson method to propose a differentially private distributed logistic regression model based on both public and private data. We try our algorithm on three different data sets, and show its advantage over: (1) a logistic regression model based solely on public data, and (2) a differentially private distributed logistic regression model based on private data under various scenarios. Logistic regression models built with our new algorithm based on both private and public datasets demonstrate better utility than models that trained on private or public datasets alone without sacrificing the rigorous privacy guarantee.

Logistic regression analysis of conventional ultrasonography, strain elastosonography, and contrast-enhanced ultrasound characteristics for the differentiation of benign and malignant thyroid nodules

PubMed Central

Deng, Yingyuan; Wang, Tianfu; Chen, Siping; Liu, Weixiang

2017-01-01

The aim of the study is to screen the significant sonographic features by logistic regression analysis and fit a model to diagnose thyroid nodules. A total of 525 pathological thyroid nodules were retrospectively analyzed. All the nodules underwent conventional ultrasonography (US), strain elastosonography (SE), and contrast -enhanced ultrasound (CEUS). Those nodules’ 12 suspicious sonographic features were used to assess thyroid nodules. The significant features of diagnosing thyroid nodules were picked out by logistic regression analysis. All variables that were statistically related to diagnosis of thyroid nodules, at a level of p < 0.05 were embodied in a logistic regression analysis model. The significant features in the logistic regression model of diagnosing thyroid nodules were calcification, suspected cervical lymph node metastasis, hypoenhancement pattern, margin, shape, vascularity, posterior acoustic, echogenicity, and elastography score. According to the results of logistic regression analysis, the formula that could predict whether or not thyroid nodules are malignant was established. The area under the receiver operating curve (ROC) was 0.930 and the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 83.77%, 89.56%, 87.05%, 86.04%, and 87.79% respectively. PMID:29228030

Logistic regression analysis of conventional ultrasonography, strain elastosonography, and contrast-enhanced ultrasound characteristics for the differentiation of benign and malignant thyroid nodules.

PubMed

Pang, Tiantian; Huang, Leidan; Deng, Yingyuan; Wang, Tianfu; Chen, Siping; Gong, Xuehao; Liu, Weixiang

2017-01-01

The aim of the study is to screen the significant sonographic features by logistic regression analysis and fit a model to diagnose thyroid nodules. A total of 525 pathological thyroid nodules were retrospectively analyzed. All the nodules underwent conventional ultrasonography (US), strain elastosonography (SE), and contrast -enhanced ultrasound (CEUS). Those nodules' 12 suspicious sonographic features were used to assess thyroid nodules. The significant features of diagnosing thyroid nodules were picked out by logistic regression analysis. All variables that were statistically related to diagnosis of thyroid nodules, at a level of p < 0.05 were embodied in a logistic regression analysis model. The significant features in the logistic regression model of diagnosing thyroid nodules were calcification, suspected cervical lymph node metastasis, hypoenhancement pattern, margin, shape, vascularity, posterior acoustic, echogenicity, and elastography score. According to the results of logistic regression analysis, the formula that could predict whether or not thyroid nodules are malignant was established. The area under the receiver operating curve (ROC) was 0.930 and the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 83.77%, 89.56%, 87.05%, 86.04%, and 87.79% respectively.

Prevalence and Determinants of Preterm Birth in Tehran, Iran: A Comparison between Logistic Regression and Decision Tree Methods.

PubMed

Amini, Payam; Maroufizadeh, Saman; Samani, Reza Omani; Hamidi, Omid; Sepidarkish, Mahdi

2017-06-01

Preterm birth (PTB) is a leading cause of neonatal death and the second biggest cause of death in children under five years of age. The objective of this study was to determine the prevalence of PTB and its associated factors using logistic regression and decision tree classification methods. This cross-sectional study was conducted on 4,415 pregnant women in Tehran, Iran, from July 6-21, 2015. Data were collected by a researcher-developed questionnaire through interviews with mothers and review of their medical records. To evaluate the accuracy of the logistic regression and decision tree methods, several indices such as sensitivity, specificity, and the area under the curve were used. The PTB rate was 5.5% in this study. The logistic regression outperformed the decision tree for the classification of PTB based on risk factors. Logistic regression showed that multiple pregnancies, mothers with preeclampsia, and those who conceived with assisted reproductive technology had an increased risk for PTB ( p < 0.05). Identifying and training mothers at risk as well as improving prenatal care may reduce the PTB rate. We also recommend that statisticians utilize the logistic regression model for the classification of risk groups for PTB.

Methods for estimating the magnitude and frequency of peak streamflows at ungaged sites in and near the Oklahoma Panhandle

USGS Publications Warehouse

Smith, S. Jerrod; Lewis, Jason M.; Graves, Grant M.

2015-09-28

Generalized-least-squares multiple-linear regression analysis was used to formulate regression relations between peak-streamflow frequency statistics and basin characteristics. Contributing drainage area was the only basin characteristic determined to be statistically significant for all percentage of annual exceedance probabilities and was the only basin characteristic used in regional regression equations for estimating peak-streamflow frequency statistics on unregulated streams in and near the Oklahoma Panhandle. The regression model pseudo-coefficient of determination, converted to percent, for the Oklahoma Panhandle regional regression equations ranged from about 38 to 63 percent. The standard errors of prediction and the standard model errors for the Oklahoma Panhandle regional regression equations ranged from about 84 to 148 percent and from about 76 to 138 percent, respectively. These errors were comparable to those reported for regional peak-streamflow frequency regression equations for the High Plains areas of Texas and Colorado. The root mean square errors for the Oklahoma Panhandle regional regression equations (ranging from 3,170 to 92,000 cubic feet per second) were less than the root mean square errors for the Oklahoma statewide regression equations (ranging from 18,900 to 412,000 cubic feet per second); therefore, the Oklahoma Panhandle regional regression equations produce more accurate peak-streamflow statistic estimates for the irrigated period of record in the Oklahoma Panhandle than do the Oklahoma statewide regression equations. The regression equations developed in this report are applicable to streams that are not substantially affected by regulation, impoundment, or surface-water withdrawals. These regression equations are intended for use for stream sites with contributing drainage areas less than or equal to about 2,060 square miles, the maximum value for the independent variable used in the regression analysis.

Methods for estimating selected low-flow statistics and development of annual flow-duration statistics for Ohio

USGS Publications Warehouse

Koltun, G.F.; Kula, Stephanie P.

2013-01-01

This report presents the results of a study to develop methods for estimating selected low-flow statistics and for determining annual flow-duration statistics for Ohio streams. Regression techniques were used to develop equations for estimating 10-year recurrence-interval (10-percent annual-nonexceedance probability) low-flow yields, in cubic feet per second per square mile, with averaging periods of 1, 7, 30, and 90-day(s), and for estimating the yield corresponding to the long-term 80-percent duration flow. These equations, which estimate low-flow yields as a function of a streamflow-variability index, are based on previously published low-flow statistics for 79 long-term continuous-record streamgages with at least 10 years of data collected through water year 1997. When applied to the calibration dataset, average absolute percent errors for the regression equations ranged from 15.8 to 42.0 percent. The regression results have been incorporated into the U.S. Geological Survey (USGS) StreamStats application for Ohio (http://water.usgs.gov/osw/streamstats/ohio.html) in the form of a yield grid to facilitate estimation of the corresponding streamflow statistics in cubic feet per second. Logistic-regression equations also were developed and incorporated into the USGS StreamStats application for Ohio for selected low-flow statistics to help identify occurrences of zero-valued statistics. Quantiles of daily and 7-day mean streamflows were determined for annual and annual-seasonal (September–November) periods for each complete climatic year of streamflow-gaging station record for 110 selected streamflow-gaging stations with 20 or more years of record. The quantiles determined for each climatic year were the 99-, 98-, 95-, 90-, 80-, 75-, 70-, 60-, 50-, 40-, 30-, 25-, 20-, 10-, 5-, 2-, and 1-percent exceedance streamflows. Selected exceedance percentiles of the annual-exceedance percentiles were subsequently computed and tabulated to help facilitate consideration of the annual risk of exceedance or nonexceedance of annual and annual-seasonal-period flow-duration values. The quantiles are based on streamflow data collected through climatic year 2008.

Logistic regression for dichotomized counts.

PubMed

Preisser, John S; Das, Kalyan; Benecha, Habtamu; Stamm, John W

2016-12-01

Sometimes there is interest in a dichotomized outcome indicating whether a count variable is positive or zero. Under this scenario, the application of ordinary logistic regression may result in efficiency loss, which is quantifiable under an assumed model for the counts. In such situations, a shared-parameter hurdle model is investigated for more efficient estimation of regression parameters relating to overall effects of covariates on the dichotomous outcome, while handling count data with many zeroes. One model part provides a logistic regression containing marginal log odds ratio effects of primary interest, while an ancillary model part describes the mean count of a Poisson or negative binomial process in terms of nuisance regression parameters. Asymptotic efficiency of the logistic model parameter estimators of the two-part models is evaluated with respect to ordinary logistic regression. Simulations are used to assess the properties of the models with respect to power and Type I error, the latter investigated under both misspecified and correctly specified models. The methods are applied to data from a randomized clinical trial of three toothpaste formulations to prevent incident dental caries in a large population of Scottish schoolchildren. © The Author(s) 2014.

Predicting 30-day Hospital Readmission with Publicly Available Administrative Database. A Conditional Logistic Regression Modeling Approach.

PubMed

Zhu, K; Lou, Z; Zhou, J; Ballester, N; Kong, N; Parikh, P

2015-01-01

This article is part of the Focus Theme of Methods of Information in Medicine on "Big Data and Analytics in Healthcare". Hospital readmissions raise healthcare costs and cause significant distress to providers and patients. It is, therefore, of great interest to healthcare organizations to predict what patients are at risk to be readmitted to their hospitals. However, current logistic regression based risk prediction models have limited prediction power when applied to hospital administrative data. Meanwhile, although decision trees and random forests have been applied, they tend to be too complex to understand among the hospital practitioners. Explore the use of conditional logistic regression to increase the prediction accuracy. We analyzed an HCUP statewide inpatient discharge record dataset, which includes patient demographics, clinical and care utilization data from California. We extracted records of heart failure Medicare beneficiaries who had inpatient experience during an 11-month period. We corrected the data imbalance issue with under-sampling. In our study, we first applied standard logistic regression and decision tree to obtain influential variables and derive practically meaning decision rules. We then stratified the original data set accordingly and applied logistic regression on each data stratum. We further explored the effect of interacting variables in the logistic regression modeling. We conducted cross validation to assess the overall prediction performance of conditional logistic regression (CLR) and compared it with standard classification models. The developed CLR models outperformed several standard classification models (e.g., straightforward logistic regression, stepwise logistic regression, random forest, support vector machine). For example, the best CLR model improved the classification accuracy by nearly 20% over the straightforward logistic regression model. Furthermore, the developed CLR models tend to achieve better sensitivity of more than 10% over the standard classification models, which can be translated to correct labeling of additional 400 - 500 readmissions for heart failure patients in the state of California over a year. Lastly, several key predictor identified from the HCUP data include the disposition location from discharge, the number of chronic conditions, and the number of acute procedures. It would be beneficial to apply simple decision rules obtained from the decision tree in an ad-hoc manner to guide the cohort stratification. It could be potentially beneficial to explore the effect of pairwise interactions between influential predictors when building the logistic regression models for different data strata. Judicious use of the ad-hoc CLR models developed offers insights into future development of prediction models for hospital readmissions, which can lead to better intuition in identifying high-risk patients and developing effective post-discharge care strategies. Lastly, this paper is expected to raise the awareness of collecting data on additional markers and developing necessary database infrastructure for larger-scale exploratory studies on readmission risk prediction.

Interpretation of commonly used statistical regression models.

PubMed

Kasza, Jessica; Wolfe, Rory

2014-01-01

A review of some regression models commonly used in respiratory health applications is provided in this article. Simple linear regression, multiple linear regression, logistic regression and ordinal logistic regression are considered. The focus of this article is on the interpretation of the regression coefficients of each model, which are illustrated through the application of these models to a respiratory health research study. © 2013 The Authors. Respirology © 2013 Asian Pacific Society of Respirology.

Evaluation of logistic regression models and effect of covariates for case-control study in RNA-Seq analysis.

PubMed

Choi, Seung Hoan; Labadorf, Adam T; Myers, Richard H; Lunetta, Kathryn L; Dupuis, Josée; DeStefano, Anita L

2017-02-06

Next generation sequencing provides a count of RNA molecules in the form of short reads, yielding discrete, often highly non-normally distributed gene expression measurements. Although Negative Binomial (NB) regression has been generally accepted in the analysis of RNA sequencing (RNA-Seq) data, its appropriateness has not been exhaustively evaluated. We explore logistic regression as an alternative method for RNA-Seq studies designed to compare cases and controls, where disease status is modeled as a function of RNA-Seq reads using simulated and Huntington disease data. We evaluate the effect of adjusting for covariates that have an unknown relationship with gene expression. Finally, we incorporate the data adaptive method in order to compare false positive rates. When the sample size is small or the expression levels of a gene are highly dispersed, the NB regression shows inflated Type-I error rates but the Classical logistic and Bayes logistic (BL) regressions are conservative. Firth's logistic (FL) regression performs well or is slightly conservative. Large sample size and low dispersion generally make Type-I error rates of all methods close to nominal alpha levels of 0.05 and 0.01. However, Type-I error rates are controlled after applying the data adaptive method. The NB, BL, and FL regressions gain increased power with large sample size, large log2 fold-change, and low dispersion. The FL regression has comparable power to NB regression. We conclude that implementing the data adaptive method appropriately controls Type-I error rates in RNA-Seq analysis. Firth's logistic regression provides a concise statistical inference process and reduces spurious associations from inaccurately estimated dispersion parameters in the negative binomial framework.

Differentially private distributed logistic regression using private and public data

PubMed Central

2014-01-01

Background Privacy protecting is an important issue in medical informatics and differential privacy is a state-of-the-art framework for data privacy research. Differential privacy offers provable privacy against attackers who have auxiliary information, and can be applied to data mining models (for example, logistic regression). However, differentially private methods sometimes introduce too much noise and make outputs less useful. Given available public data in medical research (e.g. from patients who sign open-consent agreements), we can design algorithms that use both public and private data sets to decrease the amount of noise that is introduced. Methodology In this paper, we modify the update step in Newton-Raphson method to propose a differentially private distributed logistic regression model based on both public and private data. Experiments and results We try our algorithm on three different data sets, and show its advantage over: (1) a logistic regression model based solely on public data, and (2) a differentially private distributed logistic regression model based on private data under various scenarios. Conclusion Logistic regression models built with our new algorithm based on both private and public datasets demonstrate better utility than models that trained on private or public datasets alone without sacrificing the rigorous privacy guarantee. PMID:25079786

A retrospective analysis to identify the factors affecting infection in patients undergoing chemotherapy.

PubMed

Park, Ji Hyun; Kim, Hyeon-Young; Lee, Hanna; Yun, Eun Kyoung

2015-12-01

This study compares the performance of the logistic regression and decision tree analysis methods for assessing the risk factors for infection in cancer patients undergoing chemotherapy. The subjects were 732 cancer patients who were receiving chemotherapy at K university hospital in Seoul, Korea. The data were collected between March 2011 and February 2013 and were processed for descriptive analysis, logistic regression and decision tree analysis using the IBM SPSS Statistics 19 and Modeler 15.1 programs. The most common risk factors for infection in cancer patients receiving chemotherapy were identified as alkylating agents, vinca alkaloid and underlying diabetes mellitus. The logistic regression explained 66.7% of the variation in the data in terms of sensitivity and 88.9% in terms of specificity. The decision tree analysis accounted for 55.0% of the variation in the data in terms of sensitivity and 89.0% in terms of specificity. As for the overall classification accuracy, the logistic regression explained 88.0% and the decision tree analysis explained 87.2%. The logistic regression analysis showed a higher degree of sensitivity and classification accuracy. Therefore, logistic regression analysis is concluded to be the more effective and useful method for establishing an infection prediction model for patients undergoing chemotherapy. Copyright © 2015 Elsevier Ltd. All rights reserved.

Performance and strategy comparisons of human listeners and logistic regression in discriminating underwater targets.

PubMed

Yang, Lixue; Chen, Kean

2015-11-01

To improve the design of underwater target recognition systems based on auditory perception, this study compared human listeners with automatic classifiers. Performances measures and strategies in three discrimination experiments, including discriminations between man-made and natural targets, between ships and submarines, and among three types of ships, were used. In the experiments, the subjects were asked to assign a score to each sound based on how confident they were about the category to which it belonged, and logistic regression, which represents linear discriminative models, also completed three similar tasks by utilizing many auditory features. The results indicated that the performances of logistic regression improved as the ratio between inter- and intra-class differences became larger, whereas the performances of the human subjects were limited by their unfamiliarity with the targets. Logistic regression performed better than the human subjects in all tasks but the discrimination between man-made and natural targets, and the strategies employed by excellent human subjects were similar to that of logistic regression. Logistic regression and several human subjects demonstrated similar performances when discriminating man-made and natural targets, but in this case, their strategies were not similar. An appropriate fusion of their strategies led to further improvement in recognition accuracy.

Simulating land-use changes by incorporating spatial autocorrelation and self-organization in CLUE-S modeling: a case study in Zengcheng District, Guangzhou, China

NASA Astrophysics Data System (ADS)

Mei, Zhixiong; Wu, Hao; Li, Shiyun

2018-06-01

The Conversion of Land Use and its Effects at Small regional extent (CLUE-S), which is a widely used model for land-use simulation, utilizes logistic regression to estimate the relationships between land use and its drivers, and thus, predict land-use change probabilities. However, logistic regression disregards possible spatial autocorrelation and self-organization in land-use data. Autologistic regression can depict spatial autocorrelation but cannot address self-organization, while logistic regression by considering only self-organization (NElogistic regression) fails to capture spatial autocorrelation. Therefore, this study developed a regression (NE-autologistic regression) method, which incorporated both spatial autocorrelation and self-organization, to improve CLUE-S. The Zengcheng District of Guangzhou, China was selected as the study area. The land-use data of 2001, 2005, and 2009, as well as 10 typical driving factors, were used to validate the proposed regression method and the improved CLUE-S model. Then, three future land-use scenarios in 2020: the natural growth scenario, ecological protection scenario, and economic development scenario, were simulated using the improved model. Validation results showed that NE-autologistic regression performed better than logistic regression, autologistic regression, and NE-logistic regression in predicting land-use change probabilities. The spatial allocation accuracy and kappa values of NE-autologistic-CLUE-S were higher than those of logistic-CLUE-S, autologistic-CLUE-S, and NE-logistic-CLUE-S for the simulations of two periods, 2001-2009 and 2005-2009, which proved that the improved CLUE-S model achieved the best simulation and was thereby effective to a certain extent. The scenario simulation results indicated that under all three scenarios, traffic land and residential/industrial land would increase, whereas arable land and unused land would decrease during 2009-2020. Apparent differences also existed in the simulated change sizes and locations of each land-use type under different scenarios. The results not only demonstrate the validity of the improved model but also provide a valuable reference for relevant policy-makers.

Scale-invariance underlying the logistic equation and its social applications

NASA Astrophysics Data System (ADS)

Hernando, A.; Plastino, A.

2013-01-01

On the basis of dynamical principles we i) advance a derivation of the Logistic Equation (LE), widely employed (among multiple applications) in the simulation of population growth, and ii) demonstrate that scale-invariance and a mean-value constraint are sufficient and necessary conditions for obtaining it. We also generalize the LE to multi-component systems and show that the above dynamical mechanisms underlie a large number of scale-free processes. Examples are presented regarding city-populations, diffusion in complex networks, and popularity of technological products, all of them obeying the multi-component logistic equation in an either stochastic or deterministic way.

Unitary Response Regression Models

ERIC Educational Resources Information Center

Lipovetsky, S.

2007-01-01

The dependent variable in a regular linear regression is a numerical variable, and in a logistic regression it is a binary or categorical variable. In these models the dependent variable has varying values. However, there are problems yielding an identity output of a constant value which can also be modelled in a linear or logistic regression with…

Binary logistic regression-Instrument for assessing museum indoor air impact on exhibits.

PubMed

Bucur, Elena; Danet, Andrei Florin; Lehr, Carol Blaziu; Lehr, Elena; Nita-Lazar, Mihai

2017-04-01

This paper presents a new way to assess the environmental impact on historical artifacts using binary logistic regression. The prediction of the impact on the exhibits during certain pollution scenarios (environmental impact) was calculated by a mathematical model based on the binary logistic regression; it allows the identification of those environmental parameters from a multitude of possible parameters with a significant impact on exhibitions and ranks them according to their severity effect. Air quality (NO 2 , SO 2 , O 3 and PM 2.5 ) and microclimate parameters (temperature, humidity) monitoring data from a case study conducted within exhibition and storage spaces of the Romanian National Aviation Museum Bucharest have been used for developing and validating the binary logistic regression method and the mathematical model. The logistic regression analysis was used on 794 data combinations (715 to develop of the model and 79 to validate it) by a Statistical Package for Social Sciences (SPSS 20.0). The results from the binary logistic regression analysis demonstrated that from six parameters taken into consideration, four of them present a significant effect upon exhibits in the following order: O 3 >PM 2.5 >NO 2 >humidity followed at a significant distance by the effects of SO 2 and temperature. The mathematical model, developed in this study, correctly predicted 95.1 % of the cumulated effect of the environmental parameters upon the exhibits. Moreover, this model could also be used in the decisional process regarding the preventive preservation measures that should be implemented within the exhibition space. The paper presents a new way to assess the environmental impact on historical artifacts using binary logistic regression. The mathematical model developed on the environmental parameters analyzed by the binary logistic regression method could be useful in a decision-making process establishing the best measures for pollution reduction and preventive preservation of exhibits.

Determining factors influencing survival of breast cancer by fuzzy logistic regression model.

PubMed

Nikbakht, Roya; Bahrampour, Abbas

2017-01-01

Fuzzy logistic regression model can be used for determining influential factors of disease. This study explores the important factors of actual predictive survival factors of breast cancer's patients. We used breast cancer data which collected by cancer registry of Kerman University of Medical Sciences during the period of 2000-2007. The variables such as morphology, grade, age, and treatments (surgery, radiotherapy, and chemotherapy) were applied in the fuzzy logistic regression model. Performance of model was determined in terms of mean degree of membership (MDM). The study results showed that almost 41% of patients were in neoplasm and malignant group and more than two-third of them were still alive after 5-year follow-up. Based on the fuzzy logistic model, the most important factors influencing survival were chemotherapy, morphology, and radiotherapy, respectively. Furthermore, the MDM criteria show that the fuzzy logistic regression have a good fit on the data (MDM = 0.86). Fuzzy logistic regression model showed that chemotherapy is more important than radiotherapy in survival of patients with breast cancer. In addition, another ability of this model is calculating possibilistic odds of survival in cancer patients. The results of this study can be applied in clinical research. Furthermore, there are few studies which applied the fuzzy logistic models. Furthermore, we recommend using this model in various research areas.

Accounting for center in the Early External Cephalic Version trials: an empirical comparison of statistical methods to adjust for center in a multicenter trial with binary outcomes.

PubMed

Reitsma, Angela; Chu, Rong; Thorpe, Julia; McDonald, Sarah; Thabane, Lehana; Hutton, Eileen

2014-09-26

Clustering of outcomes at centers involved in multicenter trials is a type of center effect. The Consolidated Standards of Reporting Trials Statement recommends that multicenter randomized controlled trials (RCTs) should account for center effects in their analysis, however most do not. The Early External Cephalic Version (EECV) trials published in 2003 and 2011 stratified by center at randomization, but did not account for center in the analyses, and due to the nature of the intervention and number of centers, may have been prone to center effects. Using data from the EECV trials, we undertook an empirical study to compare various statistical approaches to account for center effect while estimating the impact of external cephalic version timing (early or delayed) on the outcomes of cesarean section, preterm birth, and non-cephalic presentation at the time of birth. The data from the EECV pilot trial and the EECV2 trial were merged into one dataset. Fisher's exact method was used to test the overall effect of external cephalic version timing unadjusted for center effects. Seven statistical models that accounted for center effects were applied to the data. The models included: i) the Mantel-Haenszel test, ii) logistic regression with fixed center effect and fixed treatment effect, iii) center-size weighted and iv) un-weighted logistic regression with fixed center effect and fixed treatment-by-center interaction, iv) logistic regression with random center effect and fixed treatment effect, v) logistic regression with random center effect and random treatment-by-center interaction, and vi) generalized estimating equations. For each of the three outcomes of interest approaches to account for center effect did not alter the overall findings of the trial. The results were similar for the majority of the methods used to adjust for center, illustrating the robustness of the findings. Despite literature that suggests center effect can change the estimate of effect in multicenter trials, this empirical study does not show a difference in the outcomes of the EECV trials when accounting for center effect. The EECV2 trial was registered on 30 July 30 2005 with Current Controlled Trials: ISRCTN 56498577.

Quantitative Analysis of Land Loss in Coastal Louisiana Using Remote Sensing

NASA Astrophysics Data System (ADS)

Wales, P. M.; Kuszmaul, J.; Roberts, C.

2005-12-01

For the past thirty-five years the land loss along the Louisiana Coast has been recognized as a growing problem. One of the clearest indicators of this land loss is that in 2000 smooth cord grass (spartina alterniflora) was turning brown well before its normal hibernation period. Over 100,000 acres of marsh were affected by the 2000 browning. In 2001 data were collected using low altitude helicopter based transects of the coast, with 7,400 data points being collected by researchers at the USGS, National Wetlands Research Center, and Louisiana Department of Natural Resources. The surveys contained data describing the characteristics of the marsh, including latitude, longitude, marsh condition, marsh color, percent vegetated, and marsh die-back. Creating a model that combines remote sensing images, field data, and statistical analysis to develop a methodology for estimating the margin of error in measurements of coastal land loss (erosion) is the ultimate goal of the study. A model was successfully created using a series of band combinations (used as predictive variables). The most successful band combinations or predictive variables were the braud value [(Sum Visible TM Bands - Sum Infrared TM Bands)/(Sum Visible TM Bands + Sum Infrared TM Bands)], TM band 7/ TM band 2, brightness, NDVI, wetness, vegetation index, and a 7x7 autocovariate nearest neighbor floating window. The model values were used to generate the logistic regression model. A new image was created based on the logistic regression probability equation where each pixel represents the probability of finding water or non-water at that location in each image. Pixels within each image that have a high probability of representing water have a value close to 1 and pixels with a low probability of representing water have a value close to 0. A logistic regression model is proposed that uses seven independent variables. This model yields an accurate classification in 86.5% of the locations considered in the 1997 and 2001 survey locations. When the logistic regression was modeled to the satellite imagery of the entire Louisiana Coast study area a statewide loss was estimated to be 358 mi2 to 368 mi2, from 1997 to 2001, using two different methods for estimating land loss.

Modelling of capital asset pricing by considering the lagged effects

NASA Astrophysics Data System (ADS)

Sukono; Hidayat, Y.; Bon, A. Talib bin; Supian, S.

2017-01-01

In this paper the problem of modelling the Capital Asset Pricing Model (CAPM) with the effect of the lagged is discussed. It is assumed that asset returns are analysed influenced by the market return and the return of risk-free assets. To analyse the relationship between asset returns, the market return, and the return of risk-free assets, it is conducted by using a regression equation of CAPM, and regression equation of lagged distributed CAPM. Associated with the regression equation lagged CAPM distributed, this paper also developed a regression equation of Koyck transformation CAPM. Results of development show that the regression equation of Koyck transformation CAPM has advantages, namely simple as it only requires three parameters, compared with regression equation of lagged distributed CAPM.

Least Squares Method for Equating Logistic Ability Scales: A General Approach and Evaluation. Iowa Testing Programs Occasional Papers, Number 30.

ERIC Educational Resources Information Center

Haebara, Tomokazu

When several ability scales in item response models are separately derived from different test forms administered to different samples of examinees, these scales must be equated to a common scale because their units and origins are arbitrarily determined and generally different from scale to scale. A general method for equating logistic ability…

The use of the logistic model in space motion sickness prediction

NASA Technical Reports Server (NTRS)

Lin, Karl K.; Reschke, Millard F.

1987-01-01

The one-equation and the two-equation logistic models were used to predict subjects' susceptibility to motion sickness in KC-135 parabolic flights using data from other ground-based motion sickness tests. The results show that the logistic models correctly predicted substantially more cases (an average of 13 percent) in the data subset used for model building. Overall, the logistic models ranged from 53 to 65 percent predictions of the three endpoint parameters, whereas the Bayes linear discriminant procedure ranged from 48 to 65 percent correct for the cross validation sample.

Mixed conditional logistic regression for habitat selection studies.

PubMed

Duchesne, Thierry; Fortin, Daniel; Courbin, Nicolas

2010-05-01

1. Resource selection functions (RSFs) are becoming a dominant tool in habitat selection studies. RSF coefficients can be estimated with unconditional (standard) and conditional logistic regressions. While the advantage of mixed-effects models is recognized for standard logistic regression, mixed conditional logistic regression remains largely overlooked in ecological studies. 2. We demonstrate the significance of mixed conditional logistic regression for habitat selection studies. First, we use spatially explicit models to illustrate how mixed-effects RSFs can be useful in the presence of inter-individual heterogeneity in selection and when the assumption of independence from irrelevant alternatives (IIA) is violated. The IIA hypothesis states that the strength of preference for habitat type A over habitat type B does not depend on the other habitat types also available. Secondly, we demonstrate the significance of mixed-effects models to evaluate habitat selection of free-ranging bison Bison bison. 3. When movement rules were homogeneous among individuals and the IIA assumption was respected, fixed-effects RSFs adequately described habitat selection by simulated animals. In situations violating the inter-individual homogeneity and IIA assumptions, however, RSFs were best estimated with mixed-effects regressions, and fixed-effects models could even provide faulty conclusions. 4. Mixed-effects models indicate that bison did not select farmlands, but exhibited strong inter-individual variations in their response to farmlands. Less than half of the bison preferred farmlands over forests. Conversely, the fixed-effect model simply suggested an overall selection for farmlands. 5. Conditional logistic regression is recognized as a powerful approach to evaluate habitat selection when resource availability changes. This regression is increasingly used in ecological studies, but almost exclusively in the context of fixed-effects models. Fitness maximization can imply differences in trade-offs among individuals, which can yield inter-individual differences in selection and lead to departure from IIA. These situations are best modelled with mixed-effects models. Mixed-effects conditional logistic regression should become a valuable tool for ecological research.

Using Regression Equations Built from Summary Data in the Psychological Assessment of the Individual Case: Extension to Multiple Regression

ERIC Educational Resources Information Center

Crawford, John R.; Garthwaite, Paul H.; Denham, Annie K.; Chelune, Gordon J.

2012-01-01

Regression equations have many useful roles in psychological assessment. Moreover, there is a large reservoir of published data that could be used to build regression equations; these equations could then be employed to test a wide variety of hypotheses concerning the functioning of individual cases. This resource is currently underused because…

Advanced colorectal neoplasia risk stratification by penalized logistic regression.

PubMed

Lin, Yunzhi; Yu, Menggang; Wang, Sijian; Chappell, Richard; Imperiale, Thomas F

2016-08-01

Colorectal cancer is the second leading cause of death from cancer in the United States. To facilitate the efficiency of colorectal cancer screening, there is a need to stratify risk for colorectal cancer among the 90% of US residents who are considered "average risk." In this article, we investigate such risk stratification rules for advanced colorectal neoplasia (colorectal cancer and advanced, precancerous polyps). We use a recently completed large cohort study of subjects who underwent a first screening colonoscopy. Logistic regression models have been used in the literature to estimate the risk of advanced colorectal neoplasia based on quantifiable risk factors. However, logistic regression may be prone to overfitting and instability in variable selection. Since most of the risk factors in our study have several categories, it was tempting to collapse these categories into fewer risk groups. We propose a penalized logistic regression method that automatically and simultaneously selects variables, groups categories, and estimates their coefficients by penalizing the [Formula: see text]-norm of both the coefficients and their differences. Hence, it encourages sparsity in the categories, i.e. grouping of the categories, and sparsity in the variables, i.e. variable selection. We apply the penalized logistic regression method to our data. The important variables are selected, with close categories simultaneously grouped, by penalized regression models with and without the interactions terms. The models are validated with 10-fold cross-validation. The receiver operating characteristic curves of the penalized regression models dominate the receiver operating characteristic curve of naive logistic regressions, indicating a superior discriminative performance. © The Author(s) 2013.

Using Logistic Regression To Predict the Probability of Debris Flows Occurring in Areas Recently Burned By Wildland Fires

USGS Publications Warehouse

Rupert, Michael G.; Cannon, Susan H.; Gartner, Joseph E.

2003-01-01

Logistic regression was used to predict the probability of debris flows occurring in areas recently burned by wildland fires. Multiple logistic regression is conceptually similar to multiple linear regression because statistical relations between one dependent variable and several independent variables are evaluated. In logistic regression, however, the dependent variable is transformed to a binary variable (debris flow did or did not occur), and the actual probability of the debris flow occurring is statistically modeled. Data from 399 basins located within 15 wildland fires that burned during 2000-2002 in Colorado, Idaho, Montana, and New Mexico were evaluated. More than 35 independent variables describing the burn severity, geology, land surface gradient, rainfall, and soil properties were evaluated. The models were developed as follows: (1) Basins that did and did not produce debris flows were delineated from National Elevation Data using a Geographic Information System (GIS). (2) Data describing the burn severity, geology, land surface gradient, rainfall, and soil properties were determined for each basin. These data were then downloaded to a statistics software package for analysis using logistic regression. (3) Relations between the occurrence/non-occurrence of debris flows and burn severity, geology, land surface gradient, rainfall, and soil properties were evaluated and several preliminary multivariate logistic regression models were constructed. All possible combinations of independent variables were evaluated to determine which combination produced the most effective model. The multivariate model that best predicted the occurrence of debris flows was selected. (4) The multivariate logistic regression model was entered into a GIS, and a map showing the probability of debris flows was constructed. The most effective model incorporates the percentage of each basin with slope greater than 30 percent, percentage of land burned at medium and high burn severity in each basin, particle size sorting, average storm intensity (millimeters per hour), soil organic matter content, soil permeability, and soil drainage. The results of this study demonstrate that logistic regression is a valuable tool for predicting the probability of debris flows occurring in recently-burned landscapes.

Non-linear quantitative structure-activity relationship for adenine derivatives as competitive inhibitors of adenosine deaminase

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sadat Hayatshahi, Sayyed Hamed; Abdolmaleki, Parviz; Safarian, Shahrokh

2005-12-16

Logistic regression and artificial neural networks have been developed as two non-linear models to establish quantitative structure-activity relationships between structural descriptors and biochemical activity of adenosine based competitive inhibitors, toward adenosine deaminase. The training set included 24 compounds with known k {sub i} values. The models were trained to solve two-class problems. Unlike the previous work in which multiple linear regression was used, the highest of positive charge on the molecules was recognized to be in close relation with their inhibition activity, while the electric charge on atom N1 of adenosine was found to be a poor descriptor. Consequently, themore » previously developed equation was improved and the newly formed one could predict the class of 91.66% of compounds correctly. Also optimized 2-3-1 and 3-4-1 neural networks could increase this rate to 95.83%.« less

Estimation of sex and stature using anthropometry of the upper extremity in an Australian population.

PubMed

Howley, Donna; Howley, Peter; Oxenham, Marc F

2018-06-01

Stature and a further 8 anthropometric dimensions were recorded from the arms and hands of a sample of 96 staff and students from the Australian National University and The University of Newcastle, Australia. These dimensions were used to create simple and multiple logistic regression models for sex estimation and simple and multiple linear regression equations for stature estimation of a contemporary Australian population. Overall sex classification accuracies using the models created were comparable to similar studies. The stature estimation models achieved standard errors of estimates (SEE) which were comparable to and in many cases lower than those achieved in similar research. Generic, non sex-specific models achieved similar SEEs and R 2 values to the sex-specific models indicating stature may be accurately estimated when sex is unknown. Copyright © 2018 Elsevier B.V. All rights reserved.

Homelessness among a cohort of women in street-based sex work: the need for safer environment interventions.

PubMed

Duff, Putu; Deering, Kathleen; Gibson, Kate; Tyndall, Mark; Shannon, Kate

2011-08-12

Drawing on data from a community-based prospective cohort study in Vancouver, Canada, we examined the prevalence and individual, interpersonal and work environment correlates of homelessness among 252 women in street-based sex work. Bivariate and multivariate logistic regression using generalized estimating equations (GEE) was used to examine the individual, interpersonal and work environment factors that were associated with homelessness among street-based sex workers. Among 252 women, 43.3% reported homelessness over an 18-month follow-up period. In the multivariable GEE logistic regression analysis, younger age (adjusted odds ratio [aOR] = 0.93; 95%confidence interval [95%CI] 0.93-0.98), sexual violence by non-commercial partners (aOR = 2.14; 95%CI 1.06-4.34), servicing a higher number of clients (10+ per week vs < 10) (aOR = 1.68; 95%CI 1.05-2.69), intensive, daily crack use (aOR = 1.65; 95%CI 1.11-2.45), and servicing clients in public spaces (aOR = 1.52; CI 1.00-2.31) were independently associated with sleeping on the street. These findings indicate a critical need for safer environment interventions that mitigate the social and physical risks faced by homeless FSWs and increase access to safe, secure housing for women.

Association between Nurse Staffing and In-Hospital Bone Fractures: A Retrospective Cohort Study.

PubMed

Morita, Kojiro; Matsui, Hiroki; Fushimi, Kiyohide; Yasunaga, Hideo

2017-06-01

To determine if sufficient nurse staffing reduced in-hospital fractures in acute care hospitals. The Japanese Diagnosis Procedure Combination inpatient (DPC) database from July 2010 to March 2014 linked with the Surveys for Medical Institutions. We conducted a retrospective cohort study to examine the association of inpatient nurse-to-occupied bed ratio (NBR) with in-hospital fractures. Multivariable logistic regression with generalized estimating equations was performed, adjusting for patient characteristics and hospital characteristics. We identified 770,373 patients aged 50 years or older who underwent planned major surgery for some forms of cancer or cardiovascular diseases. We used ICD-10 codes and postoperative procedure codes to identify patients with in-hospital fractures. Hospital characteristics were obtained from the "Survey of Medical Institutions and Hospital Report" and "Annual Report for Functions of Medical Institutions." Overall, 662 (0.09 percent) in-hospital fractures were identified. Logistic regression analysis showed that the proportion of in-hospital fractures in the group with the highest NBR was significantly lower than that in the group with the lowest NBR (adjusted odd ratios, 0.67; 95 percent confidence interval, 0.44-0.99; p = .048). Sufficient nurse staffing may be important to reduce postsurgical in-hospital fractures in acute care hospitals. © Health Research and Educational Trust.

Prediction of unwanted pregnancies using logistic regression, probit regression and discriminant analysis

PubMed Central

Ebrahimzadeh, Farzad; Hajizadeh, Ebrahim; Vahabi, Nasim; Almasian, Mohammad; Bakhteyar, Katayoon

2015-01-01

Background: Unwanted pregnancy not intended by at least one of the parents has undesirable consequences for the family and the society. In the present study, three classification models were used and compared to predict unwanted pregnancies in an urban population. Methods: In this cross-sectional study, 887 pregnant mothers referring to health centers in Khorramabad, Iran, in 2012 were selected by the stratified and cluster sampling; relevant variables were measured and for prediction of unwanted pregnancy, logistic regression, discriminant analysis, and probit regression models and SPSS software version 21 were used. To compare these models, indicators such as sensitivity, specificity, the area under the ROC curve, and the percentage of correct predictions were used. Results: The prevalence of unwanted pregnancies was 25.3%. The logistic and probit regression models indicated that parity and pregnancy spacing, contraceptive methods, household income and number of living male children were related to unwanted pregnancy. The performance of the models based on the area under the ROC curve was 0.735, 0.733, and 0.680 for logistic regression, probit regression, and linear discriminant analysis, respectively. Conclusion: Given the relatively high prevalence of unwanted pregnancies in Khorramabad, it seems necessary to revise family planning programs. Despite the similar accuracy of the models, if the researcher is interested in the interpretability of the results, the use of the logistic regression model is recommended. PMID:26793655

Prediction of unwanted pregnancies using logistic regression, probit regression and discriminant analysis.

PubMed

Ebrahimzadeh, Farzad; Hajizadeh, Ebrahim; Vahabi, Nasim; Almasian, Mohammad; Bakhteyar, Katayoon

2015-01-01

Unwanted pregnancy not intended by at least one of the parents has undesirable consequences for the family and the society. In the present study, three classification models were used and compared to predict unwanted pregnancies in an urban population. In this cross-sectional study, 887 pregnant mothers referring to health centers in Khorramabad, Iran, in 2012 were selected by the stratified and cluster sampling; relevant variables were measured and for prediction of unwanted pregnancy, logistic regression, discriminant analysis, and probit regression models and SPSS software version 21 were used. To compare these models, indicators such as sensitivity, specificity, the area under the ROC curve, and the percentage of correct predictions were used. The prevalence of unwanted pregnancies was 25.3%. The logistic and probit regression models indicated that parity and pregnancy spacing, contraceptive methods, household income and number of living male children were related to unwanted pregnancy. The performance of the models based on the area under the ROC curve was 0.735, 0.733, and 0.680 for logistic regression, probit regression, and linear discriminant analysis, respectively. Given the relatively high prevalence of unwanted pregnancies in Khorramabad, it seems necessary to revise family planning programs. Despite the similar accuracy of the models, if the researcher is interested in the interpretability of the results, the use of the logistic regression model is recommended.

Predictors of course in obsessive-compulsive disorder: logistic regression versus Cox regression for recurrent events.

PubMed

Kempe, P T; van Oppen, P; de Haan, E; Twisk, J W R; Sluis, A; Smit, J H; van Dyck, R; van Balkom, A J L M

2007-09-01

Two methods for predicting remissions in obsessive-compulsive disorder (OCD) treatment are evaluated. Y-BOCS measurements of 88 patients with a primary OCD (DSM-III-R) diagnosis were performed over a 16-week treatment period, and during three follow-ups. Remission at any measurement was defined as a Y-BOCS score lower than thirteen combined with a reduction of seven points when compared with baseline. Logistic regression models were compared with a Cox regression for recurrent events model. Logistic regression yielded different models at different evaluation times. The recurrent events model remained stable when fewer measurements were used. Higher baseline levels of neuroticism and more severe OCD symptoms were associated with a lower chance of remission, early age of onset and more depressive symptoms with a higher chance. Choice of outcome time affects logistic regression prediction models. Recurrent events analysis uses all information on remissions and relapses. Short- and long-term predictors for OCD remission show overlap.

Estimating the exceedance probability of rain rate by logistic regression

NASA Technical Reports Server (NTRS)

Chiu, Long S.; Kedem, Benjamin

1990-01-01

Recent studies have shown that the fraction of an area with rain intensity above a fixed threshold is highly correlated with the area-averaged rain rate. To estimate the fractional rainy area, a logistic regression model, which estimates the conditional probability that rain rate over an area exceeds a fixed threshold given the values of related covariates, is developed. The problem of dependency in the data in the estimation procedure is bypassed by the method of partial likelihood. Analyses of simulated scanning multichannel microwave radiometer and observed electrically scanning microwave radiometer data during the Global Atlantic Tropical Experiment period show that the use of logistic regression in pixel classification is superior to multiple regression in predicting whether rain rate at each pixel exceeds a given threshold, even in the presence of noisy data. The potential of the logistic regression technique in satellite rain rate estimation is discussed.

Comparison of naïve Bayes and logistic regression for computer-aided diagnosis of breast masses using ultrasound imaging

NASA Astrophysics Data System (ADS)

Cary, Theodore W.; Cwanger, Alyssa; Venkatesh, Santosh S.; Conant, Emily F.; Sehgal, Chandra M.

2012-03-01

This study compares the performance of two proven but very different machine learners, Naïve Bayes and logistic regression, for differentiating malignant and benign breast masses using ultrasound imaging. Ultrasound images of 266 masses were analyzed quantitatively for shape, echogenicity, margin characteristics, and texture features. These features along with patient age, race, and mammographic BI-RADS category were used to train Naïve Bayes and logistic regression classifiers to diagnose lesions as malignant or benign. ROC analysis was performed using all of the features and using only a subset that maximized information gain. Performance was determined by the area under the ROC curve, Az, obtained from leave-one-out cross validation. Naïve Bayes showed significant variation (Az 0.733 +/- 0.035 to 0.840 +/- 0.029, P < 0.002) with the choice of features, but the performance of logistic regression was relatively unchanged under feature selection (Az 0.839 +/- 0.029 to 0.859 +/- 0.028, P = 0.605). Out of 34 features, a subset of 6 gave the highest information gain: brightness difference, margin sharpness, depth-to-width, mammographic BI-RADs, age, and race. The probabilities of malignancy determined by Naïve Bayes and logistic regression after feature selection showed significant correlation (R2= 0.87, P < 0.0001). The diagnostic performance of Naïve Bayes and logistic regression can be comparable, but logistic regression is more robust. Since probability of malignancy cannot be measured directly, high correlation between the probabilities derived from two basic but dissimilar models increases confidence in the predictive power of machine learning models for characterizing solid breast masses on ultrasound.

[Logistic regression model of noninvasive prediction for portal hypertensive gastropathy in patients with hepatitis B associated cirrhosis].

PubMed

Wang, Qingliang; Li, Xiaojie; Hu, Kunpeng; Zhao, Kun; Yang, Peisheng; Liu, Bo

2015-05-12

To explore the risk factors of portal hypertensive gastropathy (PHG) in patients with hepatitis B associated cirrhosis and establish a Logistic regression model of noninvasive prediction. The clinical data of 234 hospitalized patients with hepatitis B associated cirrhosis from March 2012 to March 2014 were analyzed retrospectively. The dependent variable was the occurrence of PHG while the independent variables were screened by binary Logistic analysis. Multivariate Logistic regression was used for further analysis of significant noninvasive independent variables. Logistic regression model was established and odds ratio was calculated for each factor. The accuracy, sensitivity and specificity of model were evaluated by the curve of receiver operating characteristic (ROC). According to univariate Logistic regression, the risk factors included hepatic dysfunction, albumin (ALB), bilirubin (TB), prothrombin time (PT), platelet (PLT), white blood cell (WBC), portal vein diameter, spleen index, splenic vein diameter, diameter ratio, PLT to spleen volume ratio, esophageal varices (EV) and gastric varices (GV). Multivariate analysis showed that hepatic dysfunction (X1), TB (X2), PLT (X3) and splenic vein diameter (X4) were the major occurring factors for PHG. The established regression model was Logit P=-2.667+2.186X1-2.167X2+0.725X3+0.976X4. The accuracy of model for PHG was 79.1% with a sensitivity of 77.2% and a specificity of 80.8%. Hepatic dysfunction, TB, PLT and splenic vein diameter are risk factors for PHG and the noninvasive predicted Logistic regression model was Logit P=-2.667+2.186X1-2.167X2+0.725X3+0.976X4.

Variable Selection in Logistic Regression.

DTIC Science & Technology

1987-06-01

23 %. AUTIOR(.) S. CONTRACT OR GRANT NUMBE Rf.i %Z. D. Bai, P. R. Krishnaiah and . C. Zhao F49620-85- C-0008 " PERFORMING ORGANIZATION NAME AND AOORESS...d I7 IOK-TK- d 7 -I0 7’ VARIABLE SELECTION IN LOGISTIC REGRESSION Z. D. Bai, P. R. Krishnaiah and L. C. Zhao Center for Multivariate Analysis...University of Pittsburgh Center for Multivariate Analysis University of Pittsburgh Y !I VARIABLE SELECTION IN LOGISTIC REGRESSION Z- 0. Bai, P. R. Krishnaiah

Multinomial Logistic Regression Predicted Probability Map To Visualize The Influence Of Socio-Economic Factors On Breast Cancer Occurrence in Southern Karnataka

NASA Astrophysics Data System (ADS)

Madhu, B.; Ashok, N. C.; Balasubramanian, S.

2014-11-01

Multinomial logistic regression analysis was used to develop statistical model that can predict the probability of breast cancer in Southern Karnataka using the breast cancer occurrence data during 2007-2011. Independent socio-economic variables describing the breast cancer occurrence like age, education, occupation, parity, type of family, health insurance coverage, residential locality and socioeconomic status of each case was obtained. The models were developed as follows: i) Spatial visualization of the Urban- rural distribution of breast cancer cases that were obtained from the Bharat Hospital and Institute of Oncology. ii) Socio-economic risk factors describing the breast cancer occurrences were complied for each case. These data were then analysed using multinomial logistic regression analysis in a SPSS statistical software and relations between the occurrence of breast cancer across the socio-economic status and the influence of other socio-economic variables were evaluated and multinomial logistic regression models were constructed. iii) the model that best predicted the occurrence of breast cancer were identified. This multivariate logistic regression model has been entered into a geographic information system and maps showing the predicted probability of breast cancer occurrence in Southern Karnataka was created. This study demonstrates that Multinomial logistic regression is a valuable tool for developing models that predict the probability of breast cancer Occurrence in Southern Karnataka.

Comparison of Logistic Regression and Artificial Neural Network in Low Back Pain Prediction: Second National Health Survey

PubMed Central

Parsaeian, M; Mohammad, K; Mahmoudi, M; Zeraati, H

2012-01-01

Background: The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Methods: Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. Results: The area under the ROC curve (SE), root mean square and -2Loglikelihood of the logistic regression was 0.752 (0.004), 0.3832 and 14769.2, respectively. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the artificial neural network was 0.754 (0.004), 0.3770 and 14757.6, respectively. Conclusions: Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant. PMID:23113198

Comparison of logistic regression and artificial neural network in low back pain prediction: second national health survey.

PubMed

Parsaeian, M; Mohammad, K; Mahmoudi, M; Zeraati, H

2012-01-01

The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the logistic regression was 0.752 (0.004), 0.3832 and 14769.2, respectively. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the artificial neural network was 0.754 (0.004), 0.3770 and 14757.6, respectively. Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant.

Modelling of binary logistic regression for obesity among secondary students in a rural area of Kedah

NASA Astrophysics Data System (ADS)

Kamaruddin, Ainur Amira; Ali, Zalila; Noor, Norlida Mohd.; Baharum, Adam; Ahmad, Wan Muhamad Amir W.

2014-07-01

Logistic regression analysis examines the influence of various factors on a dichotomous outcome by estimating the probability of the event's occurrence. Logistic regression, also called a logit model, is a statistical procedure used to model dichotomous outcomes. In the logit model the log odds of the dichotomous outcome is modeled as a linear combination of the predictor variables. The log odds ratio in logistic regression provides a description of the probabilistic relationship of the variables and the outcome. In conducting logistic regression, selection procedures are used in selecting important predictor variables, diagnostics are used to check that assumptions are valid which include independence of errors, linearity in the logit for continuous variables, absence of multicollinearity, and lack of strongly influential outliers and a test statistic is calculated to determine the aptness of the model. This study used the binary logistic regression model to investigate overweight and obesity among rural secondary school students on the basis of their demographics profile, medical history, diet and lifestyle. The results indicate that overweight and obesity of students are influenced by obesity in family and the interaction between a student's ethnicity and routine meals intake. The odds of a student being overweight and obese are higher for a student having a family history of obesity and for a non-Malay student who frequently takes routine meals as compared to a Malay student.

Understanding logistic regression analysis.

PubMed

Sperandei, Sandro

2014-01-01

Logistic regression is used to obtain odds ratio in the presence of more than one explanatory variable. The procedure is quite similar to multiple linear regression, with the exception that the response variable is binomial. The result is the impact of each variable on the odds ratio of the observed event of interest. The main advantage is to avoid confounding effects by analyzing the association of all variables together. In this article, we explain the logistic regression procedure using examples to make it as simple as possible. After definition of the technique, the basic interpretation of the results is highlighted and then some special issues are discussed.

Kinetic analysis on precursors for iturin A production from Bacillus amyloliquefaciens BPD1.

PubMed

Wu, Jiun-Yan; Liao, Jen-Hung; Shieh, Chwen-Jen; Hsieh, Feng-Chia; Liu, Yung-Chuan

2018-06-12

In this study, the precursor effect for iturin A production was quantitatively analyzed. A strain identified as Bacillus amyloliquefaciens BPD1 (Ba-BPD1) was selected due to its ability to produce iturin A. The enhancement of iturin A production in a submerged culture was tested using various additives, including palmitic acid, oils, and complex amino acids. Among these, complex amino acids triggered the highest yield at 559 mg/L. The respective amino acids that contribute to the structure of iturin A were used as precursors. In fact, it was found that the addition of l-proline, l-glutamine, l-asparagine and l-serine could improve iturin A yield in the defined medium. However, during the kinetic analysis, all the amino acids exhibited a lower saturation level than l-serine, which exhibited a high saturation level at 1.2% resulting in an iturin A yield of 914 mg/L. In contrast, a negative effect was observed following the addition of l-tyrosine. To analyze the kinetic behavior of l-serine, three kinetic models were adopted: the kinetic order equation, the Langmuir kinetic equation, and a modified logistic equation. The regression results showed that the modified logistic model was the best fit for the kinetic behavior of l-serine as the major precursor, which could be further referred to the biosynthesis pathway of iturin A. Among the proposed processes for iturin A production, this study achieved the highest iturin A levels as a result of the addition of precursors. Copyright © 2018 The Society for Biotechnology, Japan. Published by Elsevier B.V. All rights reserved.

Adjustment of regional regression equations for urban storm-runoff quality using at-site data

USGS Publications Warehouse

Barks, C.S.

1996-01-01

Regional regression equations have been developed to estimate urban storm-runoff loads and mean concentrations using a national data base. Four statistical methods using at-site data to adjust the regional equation predictions were developed to provide better local estimates. The four adjustment procedures are a single-factor adjustment, a regression of the observed data against the predicted values, a regression of the observed values against the predicted values and additional local independent variables, and a weighted combination of a local regression with the regional prediction. Data collected at five representative storm-runoff sites during 22 storms in Little Rock, Arkansas, were used to verify, and, when appropriate, adjust the regional regression equation predictions. Comparison of observed values of stormrunoff loads and mean concentrations to the predicted values from the regional regression equations for nine constituents (chemical oxygen demand, suspended solids, total nitrogen as N, total ammonia plus organic nitrogen as N, total phosphorus as P, dissolved phosphorus as P, total recoverable copper, total recoverable lead, and total recoverable zinc) showed large prediction errors ranging from 63 percent to more than several thousand percent. Prediction errors for 6 of the 18 regional regression equations were less than 100 percent and could be considered reasonable for water-quality prediction equations. The regression adjustment procedure was used to adjust five of the regional equation predictions to improve the predictive accuracy. For seven of the regional equations the observed and the predicted values are not significantly correlated. Thus neither the unadjusted regional equations nor any of the adjustments were appropriate. The mean of the observed values was used as a simple estimator when the regional equation predictions and adjusted predictions were not appropriate.

Comparing Methodologies for Developing an Early Warning System: Classification and Regression Tree Model versus Logistic Regression. REL 2015-077

ERIC Educational Resources Information Center

Koon, Sharon; Petscher, Yaacov

2015-01-01

The purpose of this report was to explicate the use of logistic regression and classification and regression tree (CART) analysis in the development of early warning systems. It was motivated by state education leaders' interest in maintaining high classification accuracy while simultaneously improving practitioner understanding of the rules by…

A new predictive indicator for development of pressure ulcers in bedridden patients based on common laboratory tests results.

PubMed

Hatanaka, N; Yamamoto, Y; Ichihara, K; Mastuo, S; Nakamura, Y; Watanabe, M; Iwatani, Y

2008-04-01

Various scales have been devised to predict development of pressure ulcers on the basis of clinical and laboratory data, such as the Braden Scale (Braden score), which is used to monitor activity and skin conditions of bedridden patients. However, none of these scales facilitates clinically reliable prediction. To develop a clinical laboratory data-based predictive equation for the development of pressure ulcers. Subjects were 149 hospitalised patients with respiratory disorders who were monitored for the development of pressure ulcers over a 3-month period. The proportional hazards model (Cox regression) was used to analyse the results of 12 basic laboratory tests on the day of hospitalisation in comparison with Braden score. Pressure ulcers developed in 38 patients within the study period. A Cox regression model consisting solely of Braden scale items showed that none of these items contributed to significantly predicting pressure ulcers. Rather, a combination of haemoglobin (Hb), C-reactive protein (CRP), albumin (Alb), age, and gender produced the best model for prediction. Using the set of explanatory variables, we created a new indicator based on a multiple logistic regression equation. The new indicator showed high sensitivity (0.73) and specificity (0.70), and its diagnostic power was higher than that of Alb, Hb, CRP, or the Braden score alone. The new indicator may become a more useful clinical tool for predicting presser ulcers than Braden score. The new indicator warrants verification studies to facilitate its clinical implementation in the future.

Using Multiple and Logistic Regression to Estimate the Median WillCost and Probability of Cost and Schedule Overrun for Program Managers

DTIC Science & Technology

2017-03-23

PUBLIC RELEASE; DISTRIBUTION UNLIMITED Using Multiple and Logistic Regression to Estimate the Median Will- Cost and Probability of Cost and... Cost and Probability of Cost and Schedule Overrun for Program Managers Ryan C. Trudelle Follow this and additional works at: https://scholar.afit.edu...afit.edu. Recommended Citation Trudelle, Ryan C., "Using Multiple and Logistic Regression to Estimate the Median Will- Cost and Probability of Cost and

Expression of Proteins Involved in Epithelial-Mesenchymal Transition as Predictors of Metastasis and Survival in Breast Cancer Patients

DTIC Science & Technology

2013-11-01

Ptrend 0.78 0.62 0.75 Unconditional logistic regression was used to estimate odds ratios (OR) and 95 % confidence intervals (CI) for risk of node...Ptrend 0.71 0.67 Unconditional logistic regression was used to estimate odds ratios (OR) and 95 % confidence intervals (CI) for risk of high-grade tumors... logistic regression was used to estimate odds ratios (OR) and 95 % confidence intervals (CI) for the associations between each of the seven SNPs and

Logistic LASSO regression for the diagnosis of breast cancer using clinical demographic data and the BI-RADS lexicon for ultrasonography.

PubMed

Kim, Sun Mi; Kim, Yongdai; Jeong, Kuhwan; Jeong, Heeyeong; Kim, Jiyoung

2018-01-01

The aim of this study was to compare the performance of image analysis for predicting breast cancer using two distinct regression models and to evaluate the usefulness of incorporating clinical and demographic data (CDD) into the image analysis in order to improve the diagnosis of breast cancer. This study included 139 solid masses from 139 patients who underwent a ultrasonography-guided core biopsy and had available CDD between June 2009 and April 2010. Three breast radiologists retrospectively reviewed 139 breast masses and described each lesion using the Breast Imaging Reporting and Data System (BI-RADS) lexicon. We applied and compared two regression methods-stepwise logistic (SL) regression and logistic least absolute shrinkage and selection operator (LASSO) regression-in which the BI-RADS descriptors and CDD were used as covariates. We investigated the performances of these regression methods and the agreement of radiologists in terms of test misclassification error and the area under the curve (AUC) of the tests. Logistic LASSO regression was superior (P<0.05) to SL regression, regardless of whether CDD was included in the covariates, in terms of test misclassification errors (0.234 vs. 0.253, without CDD; 0.196 vs. 0.258, with CDD) and AUC (0.785 vs. 0.759, without CDD; 0.873 vs. 0.735, with CDD). However, it was inferior (P<0.05) to the agreement of three radiologists in terms of test misclassification errors (0.234 vs. 0.168, without CDD; 0.196 vs. 0.088, with CDD) and the AUC without CDD (0.785 vs. 0.844, P<0.001), but was comparable to the AUC with CDD (0.873 vs. 0.880, P=0.141). Logistic LASSO regression based on BI-RADS descriptors and CDD showed better performance than SL in predicting the presence of breast cancer. The use of CDD as a supplement to the BI-RADS descriptors significantly improved the prediction of breast cancer using logistic LASSO regression.

Using structural equation modeling to construct calibration equations relating PM2.5 mass concentration samplers to the federal reference method sampler

NASA Astrophysics Data System (ADS)

Bilonick, Richard A.; Connell, Daniel P.; Talbott, Evelyn O.; Rager, Judith R.; Xue, Tao

2015-02-01

The objective of this study was to remove systematic bias among fine particulate matter (PM2.5) mass concentration measurements made by different types of samplers used in the Pittsburgh Aerosol Research and Inhalation Epidemiology Study (PARIES). PARIES is a retrospective epidemiology study that aims to provide a comprehensive analysis of the associations between air quality and human health effects in the Pittsburgh, Pennsylvania, region from 1999 to 2008. Calibration was needed in order to minimize the amount of systematic error in PM2.5 exposure estimation as a result of including data from 97 different PM2.5 samplers at 47 monitoring sites. Ordinary regression often has been used for calibrating air quality measurements from pairs of measurement devices; however, this is only appropriate when one of the two devices (the "independent" variable) is free from random error, which is rarely the case. A group of methods known as "errors-in-variables" (e.g., Deming regression, reduced major axis regression) has been developed to handle calibration between two devices when both are subject to random error, but these methods require information on the relative sizes of the random errors for each device, which typically cannot be obtained from the observed data. When data from more than two devices (or repeats of the same device) are available, the additional information is not used to inform the calibration. A more general approach that often has been overlooked is the use of a measurement error structural equation model (SEM) that allows the simultaneous comparison of three or more devices (or repeats). The theoretical underpinnings of all of these approaches to calibration are described, and the pros and cons of each are discussed. In particular, it is shown that both ordinary regression (when used for calibration) and Deming regression are particular examples of SEMs but with substantial deficiencies. To illustrate the use of SEMs, the 7865 daily average PM2.5 mass concentration measurements made by seven collocated samplers at an urban monitoring site in Pittsburgh, Pennsylvania, were used. These samplers, which included three federal reference method (FRM) samplers, three speciation samplers, and a tapered element oscillating microbalance (TEOM), operated at various times during the 10-year PARIES study period. Because TEOM measurements are known to depend on temperature, the constructed SEM provided calibration equations relating the TEOM to the FRM and speciation samplers as a function of ambient temperature. It was shown that TEOM imprecision and TEOM bias (relative to the FRM) both decreased as temperature increased. It also was shown that the temperature dependency for bias was non-linear and followed a sigmoidal (logistic) pattern. The speciation samplers exhibited only small bias relative to the FRM samplers, although the FRM samplers were shown to be substantially more precise than both the TEOM and the speciation samplers. Comparison of the SEM results to pairwise simple linear regression results showed that the regression results can differ substantially from the correctly-derived calibration equations, especially if the less-precise device is used as the independent variable in the regression.

The alarming problems of confounding equivalence using logistic regression models in the perspective of causal diagrams.

PubMed

Yu, Yuanyuan; Li, Hongkai; Sun, Xiaoru; Su, Ping; Wang, Tingting; Liu, Yi; Yuan, Zhongshang; Liu, Yanxun; Xue, Fuzhong

2017-12-28

Confounders can produce spurious associations between exposure and outcome in observational studies. For majority of epidemiologists, adjusting for confounders using logistic regression model is their habitual method, though it has some problems in accuracy and precision. It is, therefore, important to highlight the problems of logistic regression and search the alternative method. Four causal diagram models were defined to summarize confounding equivalence. Both theoretical proofs and simulation studies were performed to verify whether conditioning on different confounding equivalence sets had the same bias-reducing potential and then to select the optimum adjusting strategy, in which logistic regression model and inverse probability weighting based marginal structural model (IPW-based-MSM) were compared. The "do-calculus" was used to calculate the true causal effect of exposure on outcome, then the bias and standard error were used to evaluate the performances of different strategies. Adjusting for different sets of confounding equivalence, as judged by identical Markov boundaries, produced different bias-reducing potential in the logistic regression model. For the sets satisfied G-admissibility, adjusting for the set including all the confounders reduced the equivalent bias to the one containing the parent nodes of the outcome, while the bias after adjusting for the parent nodes of exposure was not equivalent to them. In addition, all causal effect estimations through logistic regression were biased, although the estimation after adjusting for the parent nodes of exposure was nearest to the true causal effect. However, conditioning on different confounding equivalence sets had the same bias-reducing potential under IPW-based-MSM. Compared with logistic regression, the IPW-based-MSM could obtain unbiased causal effect estimation when the adjusted confounders satisfied G-admissibility and the optimal strategy was to adjust for the parent nodes of outcome, which obtained the highest precision. All adjustment strategies through logistic regression were biased for causal effect estimation, while IPW-based-MSM could always obtain unbiased estimation when the adjusted set satisfied G-admissibility. Thus, IPW-based-MSM was recommended to adjust for confounders set.

Use and interpretation of logistic regression in habitat-selection studies

USGS Publications Warehouse

Keating, Kim A.; Cherry, Steve

2004-01-01

 Logistic regression is an important tool for wildlife habitat-selection studies, but the method frequently has been misapplied due to an inadequate understanding of the logistic model, its interpretation, and the influence of sampling design. To promote better use of this method, we review its application and interpretation under 3 sampling designs: random, case-control, and use-availability. Logistic regression is appropriate for habitat use-nonuse studies employing random sampling and can be used to directly model the conditional probability of use in such cases. Logistic regression also is appropriate for studies employing case-control sampling designs, but careful attention is required to interpret results correctly. Unless bias can be estimated or probability of use is small for all habitats, results of case-control studies should be interpreted as odds ratios, rather than probability of use or relative probability of use. When data are gathered under a use-availability design, logistic regression can be used to estimate approximate odds ratios if probability of use is small, at least on average. More generally, however, logistic regression is inappropriate for modeling habitat selection in use-availability studies. In particular, using logistic regression to fit the exponential model of Manly et al. (2002:100) does not guarantee maximum-likelihood estimates, valid probabilities, or valid likelihoods. We show that the resource selection function (RSF) commonly used for the exponential model is proportional to a logistic discriminant function. Thus, it may be used to rank habitats with respect to probability of use and to identify important habitat characteristics or their surrogates, but it is not guaranteed to be proportional to probability of use. Other problems associated with the exponential model also are discussed. We describe an alternative model based on Lancaster and Imbens (1996) that offers a method for estimating conditional probability of use in use-availability studies. Although promising, this model fails to converge to a unique solution in some important situations. Further work is needed to obtain a robust method that is broadly applicable to use-availability studies.

Modeling Governance KB with CATPCA to Overcome Multicollinearity in the Logistic Regression

NASA Astrophysics Data System (ADS)

Khikmah, L.; Wijayanto, H.; Syafitri, U. D.

2017-04-01

The problem often encounters in logistic regression modeling are multicollinearity problems. Data that have multicollinearity between explanatory variables with the result in the estimation of parameters to be bias. Besides, the multicollinearity will result in error in the classification. In general, to overcome multicollinearity in regression used stepwise regression. They are also another method to overcome multicollinearity which involves all variable for prediction. That is Principal Component Analysis (PCA). However, classical PCA in only for numeric data. Its data are categorical, one method to solve the problems is Categorical Principal Component Analysis (CATPCA). Data were used in this research were a part of data Demographic and Population Survey Indonesia (IDHS) 2012. This research focuses on the characteristic of women of using the contraceptive methods. Classification results evaluated using Area Under Curve (AUC) values. The higher the AUC value, the better. Based on AUC values, the classification of the contraceptive method using stepwise method (58.66%) is better than the logistic regression model (57.39%) and CATPCA (57.39%). Evaluation of the results of logistic regression using sensitivity, shows the opposite where CATPCA method (99.79%) is better than logistic regression method (92.43%) and stepwise (92.05%). Therefore in this study focuses on major class classification (using a contraceptive method), then the selected model is CATPCA because it can raise the level of the major class model accuracy.

Description of Aspergillus flavus growth under the influence of different factors (water activity, incubation temperature, protein and fat concentration, pH, and cinnamon essential oil concentration) by kinetic, probability of growth, and time-to-detection models.

PubMed

Kosegarten, Carlos E; Ramírez-Corona, Nelly; Mani-López, Emma; Palou, Enrique; López-Malo, Aurelio

2017-01-02

A Box-Behnken design was used to determine the effect of protein concentration (0, 5, or 10g of casein/100g), fat (0, 3, or 6g of corn oil/100g), a w (0.900, 0.945, or 0.990), pH (3.5, 5.0, or 6.5), concentration of cinnamon essential oil (CEO, 0, 200, or 400μL/kg) and incubation temperature (15, 25, or 35°C) on the growth of Aspergillus flavus during 50days of incubation. Mold response under the evaluated conditions was modeled by the modified Gompertz equation, logistic regression, and time-to-detection model. The obtained polynomial regression models allow the significant coefficients (p<0.05) for linear, quadratic and interaction effects for the Gompertz equation's parameters to be identified, which adequately described (R 2 >0.967) the studied mold responses. After 50days of incubation, every tested model system was classified according to the observed response as 1 (growth) or 0 (no growth), then a binary logistic regression was utilized to model A. flavus growth interface, allowing to predict the probability of mold growth under selected combinations of tested factors. The time-to-detection model was utilized to estimate the time at which A. flavus visible growth begins. Water activity, temperature, and CEO concentration were the most important factors affecting fungal growth. It was observed that there is a range of possible combinations that may induce growth, such that incubation conditions and the amount of essential oil necessary for fungal growth inhibition strongly depend on protein and fat concentrations as well as on the pH of studied model systems. The probabilistic model and the time-to-detection models constitute another option to determine appropriate storage/processing conditions and accurately predict the probability and/or the time at which A. flavus growth occurs. Copyright © 2016 Elsevier B.V. All rights reserved.

Association Between Depression and Elder Abuse and the Mediation of Social Support: A Cross-Sectional Study of Elder Females in Mexico City.

PubMed

Vilar-Compte, Mireya; Giraldo-Rodríguez, Liliana; Ochoa-Laginas, Adriana; Gaitan-Rossi, Pablo

2018-04-01

We assessed the association between depression and elder abuse, and the mediation effect of social support among elder women in Mexico City. A total of 526 noninstitutionalized elder women, residing in Mexico City and attending public community centers were selected. Logistic regressions and structural equation models (SEM) were estimated. One fifth of the elderly women were at risk of depression, one third suffered some type of abuse in the past 12 months, and 82% reported low social support. Logistic models confirmed that depression was statistically associated with elder abuse and vice versa (odds ratio [OR] = 1.97 and 1.96, respectively). In both models, social support significantly reduced the association between these variables leading to study these associations through SEM. This approach highlighted that social support buffers the association between depression and elder abuse. Findings underline the relevance of programs and strategies targeted at increasing social support among urban older adults.

Logistic regression models of factors influencing the location of bioenergy and biofuels plants

Treesearch

T.M. Young; R.L. Zaretzki; J.H. Perdue; F.M. Guess; X. Liu

2011-01-01

Logistic regression models were developed to identify significant factors that influence the location of existing wood-using bioenergy/biofuels plants and traditional wood-using facilities. Logistic models provided quantitative insight for variables influencing the location of woody biomass-using facilities. Availability of "thinnings to a basal area of 31.7m2/ha...

On the effects of nonlinear boundary conditions in diffusive logistic equations on bounded domains

NASA Astrophysics Data System (ADS)

Cantrell, Robert Stephen; Cosner, Chris

We study a diffusive logistic equation with nonlinear boundary conditions. The equation arises as a model for a population that grows logistically inside a patch and crosses the patch boundary at a rate that depends on the population density. Specifically, the rate at which the population crosses the boundary is assumed to decrease as the density of the population increases. The model is motivated by empirical work on the Glanville fritillary butterfly. We derive local and global bifurcation results which show that the model can have multiple equilibria and in some parameter ranges can support Allee effects. The analysis leads to eigenvalue problems with nonstandard boundary conditions.

Discrete post-processing of total cloud cover ensemble forecasts

NASA Astrophysics Data System (ADS)

Hemri, Stephan; Haiden, Thomas; Pappenberger, Florian

2017-04-01

This contribution presents an approach to post-process ensemble forecasts for the discrete and bounded weather variable of total cloud cover. Two methods for discrete statistical post-processing of ensemble predictions are tested. The first approach is based on multinomial logistic regression, the second involves a proportional odds logistic regression model. Applying them to total cloud cover raw ensemble forecasts from the European Centre for Medium-Range Weather Forecasts improves forecast skill significantly. Based on station-wise post-processing of raw ensemble total cloud cover forecasts for a global set of 3330 stations over the period from 2007 to early 2014, the more parsimonious proportional odds logistic regression model proved to slightly outperform the multinomial logistic regression model. Reference Hemri, S., Haiden, T., & Pappenberger, F. (2016). Discrete post-processing of total cloud cover ensemble forecasts. Monthly Weather Review 144, 2565-2577.

Fuzzy multinomial logistic regression analysis: A multi-objective programming approach

NASA Astrophysics Data System (ADS)

Abdalla, Hesham A.; El-Sayed, Amany A.; Hamed, Ramadan

2017-05-01

Parameter estimation for multinomial logistic regression is usually based on maximizing the likelihood function. For large well-balanced datasets, Maximum Likelihood (ML) estimation is a satisfactory approach. Unfortunately, ML can fail completely or at least produce poor results in terms of estimated probabilities and confidence intervals of parameters, specially for small datasets. In this study, a new approach based on fuzzy concepts is proposed to estimate parameters of the multinomial logistic regression. The study assumes that the parameters of multinomial logistic regression are fuzzy. Based on the extension principle stated by Zadeh and Bárdossy's proposition, a multi-objective programming approach is suggested to estimate these fuzzy parameters. A simulation study is used to evaluate the performance of the new approach versus Maximum likelihood (ML) approach. Results show that the new proposed model outperforms ML in cases of small datasets.

A Primer on Logistic Regression.

ERIC Educational Resources Information Center

Woldbeck, Tanya

This paper introduces logistic regression as a viable alternative when the researcher is faced with variables that are not continuous. If one is to use simple regression, the dependent variable must be measured on a continuous scale. In the behavioral sciences, it may not always be appropriate or possible to have a measured dependent variable on a…

Alternative Regression Equations for Estimation of Annual Peak-Streamflow Frequency for Undeveloped Watersheds in Texas using PRESS Minimization

USGS Publications Warehouse

Asquith, William H.; Thompson, David B.

2008-01-01

The U.S. Geological Survey, in cooperation with the Texas Department of Transportation and in partnership with Texas Tech University, investigated a refinement of the regional regression method and developed alternative equations for estimation of peak-streamflow frequency for undeveloped watersheds in Texas. A common model for estimation of peak-streamflow frequency is based on the regional regression method. The current (2008) regional regression equations for 11 regions of Texas are based on log10 transformations of all regression variables (drainage area, main-channel slope, and watershed shape). Exclusive use of log10-transformation does not fully linearize the relations between the variables. As a result, some systematic bias remains in the current equations. The bias results in overestimation of peak streamflow for both the smallest and largest watersheds. The bias increases with increasing recurrence interval. The primary source of the bias is the discernible curvilinear relation in log10 space between peak streamflow and drainage area. Bias is demonstrated by selected residual plots with superimposed LOWESS trend lines. To address the bias, a statistical framework based on minimization of the PRESS statistic through power transformation of drainage area is described and implemented, and the resulting regression equations are reported. Compared to log10-exclusive equations, the equations derived from PRESS minimization have PRESS statistics and residual standard errors less than the log10 exclusive equations. Selected residual plots for the PRESS-minimized equations are presented to demonstrate that systematic bias in regional regression equations for peak-streamflow frequency estimation in Texas can be reduced. Because the overall error is similar to the error associated with previous equations and because the bias is reduced, the PRESS-minimized equations reported here provide alternative equations for peak-streamflow frequency estimation.

[Influences of environmental factors and interaction of several chemokines gene-environmental on systemic lupus erythematosus].

PubMed

Ye, Dong-qing; Hu, Yi-song; Li, Xiang-pei; Huang, Fen; Yang, Shi-gui; Hao, Jia-hu; Yin, Jing; Zhang, Guo-qing; Liu, Hui-hui

2004-11-01

To explore the impact of environmental factors, daily lifestyle, psycho-social factors and the interactions between environmental factors and chemokines genes on systemic lupus erythematosus (SLE). Case-control study was carried out and environmental factors for SLE were analyzed by univariate and multivariate unconditional logistic regression. Interactions between environmental factors and chemokines polymorphism contributing to systemic lupus erythematosus were also analyzed by logistic regression model. There were nineteen factors associated with SLE when univariate unconditional logistic regression was used. However, when multivariate unconditional logistic regression was used, only five factors showed having impacts on the disease, in which drinking well water (OR=0.099) was protective factor for SLE, and multiple drug allergy (OR=8.174), over-exposure to sunshine (OR=18.339), taking antibiotics (OR=9.630) and oral contraceptives were risk factors for SLE. When unconditional logistic regression model was used, results showed that there was interaction between eating irritable food and -2518MCP-1G/G genotype (OR=4.387). No interaction between environmental factors was found that contributing to SLE in this study. Many environmental factors were related to SLE, and there was an interaction between -2518MCP-1G/G genotype and eating irritable food.

A deeper look at two concepts of measuring gene-gene interactions: logistic regression and interaction information revisited.

PubMed

Mielniczuk, Jan; Teisseyre, Paweł

2018-03-01

Detection of gene-gene interactions is one of the most important challenges in genome-wide case-control studies. Besides traditional logistic regression analysis, recently the entropy-based methods attracted a significant attention. Among entropy-based methods, interaction information is one of the most promising measures having many desirable properties. Although both logistic regression and interaction information have been used in several genome-wide association studies, the relationship between them has not been thoroughly investigated theoretically. The present paper attempts to fill this gap. We show that although certain connections between the two methods exist, in general they refer two different concepts of dependence and looking for interactions in those two senses leads to different approaches to interaction detection. We introduce ordering between interaction measures and specify conditions for independent and dependent genes under which interaction information is more discriminative measure than logistic regression. Moreover, we show that for so-called perfect distributions those measures are equivalent. The numerical experiments illustrate the theoretical findings indicating that interaction information and its modified version are more universal tools for detecting various types of interaction than logistic regression and linkage disequilibrium measures. © 2017 WILEY PERIODICALS, INC.

Controlling Type I Error Rates in Assessing DIF for Logistic Regression Method Combined with SIBTEST Regression Correction Procedure and DIF-Free-Then-DIF Strategy

ERIC Educational Resources Information Center

Shih, Ching-Lin; Liu, Tien-Hsiang; Wang, Wen-Chung

2014-01-01

The simultaneous item bias test (SIBTEST) method regression procedure and the differential item functioning (DIF)-free-then-DIF strategy are applied to the logistic regression (LR) method simultaneously in this study. These procedures are used to adjust the effects of matching true score on observed score and to better control the Type I error…

Understanding the Personality and Behavioral Mechanisms Defining Hypersexuality in Men Who Have Sex with Men

PubMed Central

Miner, Michael H.; Romine, Rebecca Swinburne; Raymond, Nancy; Janssen, Erick; MacDonald, Angus; Coleman, Eli

2016-01-01

Objective The purpose of this study was to investigate personality factors and behavioral mechanisms that are relevant to hypersexuality in men who have sex with men. Method A sample of 242 men who have sex with men were recruited from various sites in a moderate size mid-western city. Participants were assigned to hypersexuality or control group using a SCID-type interview. Self-report inventories were administered that measured the broad band personality constructs of positive emotionality, negative emotionality and constraint, and more narrow constructs related to sexual behavioral control, behavioral activation, behavioral inhibition, sexual excitation, sexual inhibition, impulsivity, ADHD, and sexual behavior. Hierarchical logistic regression was used to determine the relationship between these personality and behavioral variables and group membership. Results A hierarchical logistic regression, controlling for age, revealed a significant positive relationship between hypersexuality and negative emotionality and a negative relationship with constraint. None of the behavioral mechanism variables entered this equation. However, a hierarchical multiple regression predicting sexual behavioral control indicated that lack of such control was positively related to sexual excitation and sexual inhibition due to the threat of performance failure and negatively related to sexual inhibition due to the threat of performance consequences and general behavioral inhibition Conclusions Hypersexuality was found to be related to two broad personality factors that are characterized by emotional reactivity, risk-taking, and impulsivity. The associated lack of sexual behavior control is influenced by both sexual excitatory and inhibitory mechanisms, but not general behavioral activation and inhibitory mechanisms. PMID:27486137

Dry season mean monthly flow and harmonic mean flow regression equations for selected ungaged basins in Arkansas

USGS Publications Warehouse

Breaker, Brian K.

2015-01-01

Equations for two regions were found to be statistically significant for developing regression equations for estimating harmonic mean flows at ungaged basins; thus, equations are applicable only to streams in those respective regions in Arkansas. Regression equations for dry season mean monthly flows are applicable only to streams located throughout Arkansas. All regression equations are applicable only to unaltered streams where flows were not significantly affected by regulation, diversion, or urbanization. The median number of years used for dry season mean monthly flow calculation was 43, and the median number of years used for harmonic mean flow calculations was 34 for region 1 and 43 for region 2.

Access disparities to Magnet hospitals for patients undergoing neurosurgical operations

PubMed Central

Missios, Symeon; Bekelis, Kimon

2017-01-01

Background Centers of excellence focusing on quality improvement have demonstrated superior outcomes for a variety of surgical interventions. We investigated the presence of access disparities to hospitals recognized by the Magnet Recognition Program of the American Nurses Credentialing Center (ANCC) for patients undergoing neurosurgical operations. Methods We performed a cohort study of all neurosurgery patients who were registered in the New York Statewide Planning and Research Cooperative System (SPARCS) database from 2009–2013. We examined the association of African-American race and lack of insurance with Magnet status hospitalization for neurosurgical procedures. A mixed effects propensity adjusted multivariable regression analysis was used to control for confounding. Results During the study period, 190,535 neurosurgical patients met the inclusion criteria. Using a multivariable logistic regression, we demonstrate that African-Americans had lower admission rates to Magnet institutions (OR 0.62; 95% CI, 0.58–0.67). This persisted in a mixed effects logistic regression model (OR 0.77; 95% CI, 0.70–0.83) to adjust for clustering at the patient county level, and a propensity score adjusted logistic regression model (OR 0.75; 95% CI, 0.69–0.82). Additionally, lack of insurance was associated with lower admission rates to Magnet institutions (OR 0.71; 95% CI, 0.68–0.73), in a multivariable logistic regression model. This persisted in a mixed effects logistic regression model (OR 0.72; 95% CI, 0.69–0.74), and a propensity score adjusted logistic regression model (OR 0.72; 95% CI, 0.69–0.75). Conclusions Using a comprehensive all-payer cohort of neurosurgery patients in New York State we identified an association of African-American race and lack of insurance with lower rates of admission to Magnet hospitals. PMID:28684152

Adjusting for Confounding in Early Postlaunch Settings: Going Beyond Logistic Regression Models.

PubMed

Schmidt, Amand F; Klungel, Olaf H; Groenwold, Rolf H H

2016-01-01

Postlaunch data on medical treatments can be analyzed to explore adverse events or relative effectiveness in real-life settings. These analyses are often complicated by the number of potential confounders and the possibility of model misspecification. We conducted a simulation study to compare the performance of logistic regression, propensity score, disease risk score, and stabilized inverse probability weighting methods to adjust for confounding. Model misspecification was induced in the independent derivation dataset. We evaluated performance using relative bias confidence interval coverage of the true effect, among other metrics. At low events per coefficient (1.0 and 0.5), the logistic regression estimates had a large relative bias (greater than -100%). Bias of the disease risk score estimates was at most 13.48% and 18.83%. For the propensity score model, this was 8.74% and >100%, respectively. At events per coefficient of 1.0 and 0.5, inverse probability weighting frequently failed or reduced to a crude regression, resulting in biases of -8.49% and 24.55%. Coverage of logistic regression estimates became less than the nominal level at events per coefficient ≤5. For the disease risk score, inverse probability weighting, and propensity score, coverage became less than nominal at events per coefficient ≤2.5, ≤1.0, and ≤1.0, respectively. Bias of misspecified disease risk score models was 16.55%. In settings with low events/exposed subjects per coefficient, disease risk score methods can be useful alternatives to logistic regression models, especially when propensity score models cannot be used. Despite better performance of disease risk score methods than logistic regression and propensity score models in small events per coefficient settings, bias, and coverage still deviated from nominal.

Religious coping, spirituality, and substance use and abuse among youth in high-risk communities in San Salvador, El Salvador.

PubMed

Salas-Wright, Christopher P; Olate, Rene; Vaughn, Michael G

2013-06-01

Little is known about the relationship between religious coping, spirituality, and substance use in developing nations such as El Salvador. Collected in 2011, the sample consists of 290 high-risk and gang-involved adolescents (11-17 years) and young adults (18-25 years) in San Salvador, El Salvador. Structural equation modeling and logistic regression are employed to examine the associations between the Measure of Religious Coping (RCOPE), the Intrinsic Spirituality Scale, and substance use and abuse. Results suggest that spirituality and, to a far lesser degree, religious coping may serve to protect for substance use and abuse among this high-risk population of Salvadoran youth.

On the use and misuse of scalar scores of confounders in design and analysis of observational studies.

PubMed

Pfeiffer, R M; Riedl, R

2015-08-15

We assess the asymptotic bias of estimates of exposure effects conditional on covariates when summary scores of confounders, instead of the confounders themselves, are used to analyze observational data. First, we study regression models for cohort data that are adjusted for summary scores. Second, we derive the asymptotic bias for case-control studies when cases and controls are matched on a summary score, and then analyzed either using conditional logistic regression or by unconditional logistic regression adjusted for the summary score. Two scores, the propensity score (PS) and the disease risk score (DRS) are studied in detail. For cohort analysis, when regression models are adjusted for the PS, the estimated conditional treatment effect is unbiased only for linear models, or at the null for non-linear models. Adjustment of cohort data for DRS yields unbiased estimates only for linear regression; all other estimates of exposure effects are biased. Matching cases and controls on DRS and analyzing them using conditional logistic regression yields unbiased estimates of exposure effect, whereas adjusting for the DRS in unconditional logistic regression yields biased estimates, even under the null hypothesis of no association. Matching cases and controls on the PS yield unbiased estimates only under the null for both conditional and unconditional logistic regression, adjusted for the PS. We study the bias for various confounding scenarios and compare our asymptotic results with those from simulations with limited sample sizes. To create realistic correlations among multiple confounders, we also based simulations on a real dataset. Copyright © 2015 John Wiley & Sons, Ltd.

[Application of SAS macro to evaluated multiplicative and additive interaction in logistic and Cox regression in clinical practices].

PubMed

Nie, Z Q; Ou, Y Q; Zhuang, J; Qu, Y J; Mai, J Z; Chen, J M; Liu, X Q

2016-05-01

Conditional logistic regression analysis and unconditional logistic regression analysis are commonly used in case control study, but Cox proportional hazard model is often used in survival data analysis. Most literature only refer to main effect model, however, generalized linear model differs from general linear model, and the interaction was composed of multiplicative interaction and additive interaction. The former is only statistical significant, but the latter has biological significance. In this paper, macros was written by using SAS 9.4 and the contrast ratio, attributable proportion due to interaction and synergy index were calculated while calculating the items of logistic and Cox regression interactions, and the confidence intervals of Wald, delta and profile likelihood were used to evaluate additive interaction for the reference in big data analysis in clinical epidemiology and in analysis of genetic multiplicative and additive interactions.

Low-flow, base-flow, and mean-flow regression equations for Pennsylvania streams

USGS Publications Warehouse

Stuckey, Marla H.

2006-01-01

Low-flow, base-flow, and mean-flow characteristics are an important part of assessing water resources in a watershed. These streamflow characteristics can be used by watershed planners and regulators to determine water availability, water-use allocations, assimilative capacities of streams, and aquatic-habitat needs. Streamflow characteristics are commonly predicted by use of regression equations when a nearby streamflow-gaging station is not available. Regression equations for predicting low-flow, base-flow, and mean-flow characteristics for Pennsylvania streams were developed from data collected at 293 continuous- and partial-record streamflow-gaging stations with flow unaffected by upstream regulation, diversion, or mining. Continuous-record stations used in the regression analysis had 9 years or more of data, and partial-record stations used had seven or more measurements collected during base-flow conditions. The state was divided into five low-flow regions and regional regression equations were developed for the 7-day, 10-year; 7-day, 2-year; 30-day, 10-year; 30-day, 2-year; and 90-day, 10-year low flows using generalized least-squares regression. Statewide regression equations were developed for the 10-year, 25-year, and 50-year base flows using generalized least-squares regression. Statewide regression equations were developed for harmonic mean and mean annual flow using weighted least-squares regression. Basin characteristics found to be significant explanatory variables at the 95-percent confidence level for one or more regression equations were drainage area, basin slope, thickness of soil, stream density, mean annual precipitation, mean elevation, and the percentage of glaciation, carbonate bedrock, forested area, and urban area within a basin. Standard errors of prediction ranged from 33 to 66 percent for the n-day, T-year low flows; 21 to 23 percent for the base flows; and 12 to 38 percent for the mean annual flow and harmonic mean, respectively. The regression equations are not valid in watersheds with upstream regulation, diversions, or mining activities. Watersheds with karst features need close examination as to the applicability of the regression-equation results.

About Global Stable of Solutions of Logistic Equation with Delay

NASA Astrophysics Data System (ADS)

Kaschenko, S. A.; Loginov, D. O.

2017-12-01

The article is devoted to the definition of all the arguments for which all positive solutions of logistic equation with delay tend to zero for t → ∞. The authors have proved the acquainted Wright’s conjecture on evaluation of a multitude of such arguments. An approach that enables subsequent refinement of this evaluation has been developed.

Score Equating and Item Response Theory: Some Practical Considerations.

ERIC Educational Resources Information Center

Cook, Linda L.; Eignor, Daniel R.

The purposes of this paper are five-fold to discuss: (1) when item response theory (IRT) equating methods should provide better results than traditional methods; (2) which IRT model, the three-parameter logistic or the one-parameter logistic (Rasch), is the most reasonable to use; (3) what unique contributions IRT methods can offer the equating…

No rationale for 1 variable per 10 events criterion for binary logistic regression analysis.

PubMed

van Smeden, Maarten; de Groot, Joris A H; Moons, Karel G M; Collins, Gary S; Altman, Douglas G; Eijkemans, Marinus J C; Reitsma, Johannes B

2016-11-24

Ten events per variable (EPV) is a widely advocated minimal criterion for sample size considerations in logistic regression analysis. Of three previous simulation studies that examined this minimal EPV criterion only one supports the use of a minimum of 10 EPV. In this paper, we examine the reasons for substantial differences between these extensive simulation studies. The current study uses Monte Carlo simulations to evaluate small sample bias, coverage of confidence intervals and mean square error of logit coefficients. Logistic regression models fitted by maximum likelihood and a modified estimation procedure, known as Firth's correction, are compared. The results show that besides EPV, the problems associated with low EPV depend on other factors such as the total sample size. It is also demonstrated that simulation results can be dominated by even a few simulated data sets for which the prediction of the outcome by the covariates is perfect ('separation'). We reveal that different approaches for identifying and handling separation leads to substantially different simulation results. We further show that Firth's correction can be used to improve the accuracy of regression coefficients and alleviate the problems associated with separation. The current evidence supporting EPV rules for binary logistic regression is weak. Given our findings, there is an urgent need for new research to provide guidance for supporting sample size considerations for binary logistic regression analysis.

4D-Fingerprint Categorical QSAR Models for Skin Sensitization Based on Classification Local Lymph Node Assay Measures

PubMed Central

Li, Yi; Tseng, Yufeng J.; Pan, Dahua; Liu, Jianzhong; Kern, Petra S.; Gerberick, G. Frank; Hopfinger, Anton J.

2008-01-01

Currently, the only validated methods to identify skin sensitization effects are in vivo models, such as the Local Lymph Node Assay (LLNA) and guinea pig studies. There is a tremendous need, in particular due to novel legislation, to develop animal alternatives, eg. Quantitative Structure-Activity Relationship (QSAR) models. Here, QSAR models for skin sensitization using LLNA data have been constructed. The descriptors used to generate these models are derived from the 4D-molecular similarity paradigm and are referred to as universal 4D-fingerprints. A training set of 132 structurally diverse compounds and a test set of 15 structurally diverse compounds were used in this study. The statistical methodologies used to build the models are logistic regression (LR), and partial least square coupled logistic regression (PLS-LR), which prove to be effective tools for studying skin sensitization measures expressed in the two categorical terms of sensitizer and non-sensitizer. QSAR models with low values of the Hosmer-Lemeshow goodness-of-fit statistic, χHL2, are significant and predictive. For the training set, the cross-validated prediction accuracy of the logistic regression models ranges from 77.3% to 78.0%, while that of PLS-logistic regression models ranges from 87.1% to 89.4%. For the test set, the prediction accuracy of logistic regression models ranges from 80.0%-86.7%, while that of PLS-logistic regression models ranges from 73.3%-80.0%. The QSAR models are made up of 4D-fingerprints related to aromatic atoms, hydrogen bond acceptors and negatively partially charged atoms. PMID:17226934

MODELING SNAKE MICROHABITAT FROM RADIOTELEMETRY STUDIES USING POLYTOMOUS LOGISTIC REGRESSION

EPA Science Inventory

Multivariate analysis of snake microhabitat has historically used techniques that were derived under assumptions of normality and common covariance structure (e.g., discriminant function analysis, MANOVA). In this study, polytomous logistic regression (PLR which does not require ...

Regional Regression Equations to Estimate Flow-Duration Statistics at Ungaged Stream Sites in Connecticut

USGS Publications Warehouse

Ahearn, Elizabeth A.

2010-01-01

Multiple linear regression equations for determining flow-duration statistics were developed to estimate select flow exceedances ranging from 25- to 99-percent for six 'bioperiods'-Salmonid Spawning (November), Overwinter (December-February), Habitat Forming (March-April), Clupeid Spawning (May), Resident Spawning (June), and Rearing and Growth (July-October)-in Connecticut. Regression equations also were developed to estimate the 25- and 99-percent flow exceedances without reference to a bioperiod. In total, 32 equations were developed. The predictive equations were based on regression analyses relating flow statistics from streamgages to GIS-determined basin and climatic characteristics for the drainage areas of those streamgages. Thirty-nine streamgages (and an additional 6 short-term streamgages and 28 partial-record sites for the non-bioperiod 99-percent exceedance) in Connecticut and adjacent areas of neighboring States were used in the regression analysis. Weighted least squares regression analysis was used to determine the predictive equations; weights were assigned based on record length. The basin characteristics-drainage area, percentage of area with coarse-grained stratified deposits, percentage of area with wetlands, mean monthly precipitation (November), mean seasonal precipitation (December, January, and February), and mean basin elevation-are used as explanatory variables in the equations. Standard errors of estimate of the 32 equations ranged from 10.7 to 156 percent with medians of 19.2 and 55.4 percent to predict the 25- and 99-percent exceedances, respectively. Regression equations to estimate high and median flows (25- to 75-percent exceedances) are better predictors (smaller variability of the residual values around the regression line) than the equations to estimate low flows (less than 75-percent exceedance). The Habitat Forming (March-April) bioperiod had the smallest standard errors of estimate, ranging from 10.7 to 20.9 percent. In contrast, the Rearing and Growth (July-October) bioperiod had the largest standard errors, ranging from 30.9 to 156 percent. The adjusted coefficient of determination of the equations ranged from 77.5 to 99.4 percent with medians of 98.5 and 90.6 percent to predict the 25- and 99-percent exceedances, respectively. Descriptive information on the streamgages used in the regression, measured basin and climatic characteristics, and estimated flow-duration statistics are provided in this report. Flow-duration statistics and the 32 regression equations for estimating flow-duration statistics in Connecticut are stored on the U.S. Geological Survey World Wide Web application ?StreamStats? (http://water.usgs.gov/osw/streamstats/index.html). The regression equations developed in this report can be used to produce unbiased estimates of select flow exceedances statewide.

Nationwide summary of US Geological Survey regional regression equations for estimating magnitude and frequency of floods for ungaged sites, 1993

USGS Publications Warehouse

Jennings, M.E.; Thomas, W.O.; Riggs, H.C.

1994-01-01

For many years, the U.S. Geological Survey (USGS) has been involved in the development of regional regression equations for estimating flood magnitude and frequency at ungaged sites. These regression equations are used to transfer flood characteristics from gaged to ungaged sites through the use of watershed and climatic characteristics as explanatory or predictor variables. Generally these equations have been developed on a statewide or metropolitan area basis as part of cooperative study programs with specific State Departments of Transportation or specific cities. The USGS, in cooperation with the Federal Highway Administration and the Federal Emergency Management Agency, has compiled all the current (as of September 1993) statewide and metropolitan area regression equations into a micro-computer program titled the National Flood Frequency Program.This program includes regression equations for estimating flood-peak discharges and techniques for estimating a typical flood hydrograph for a given recurrence interval peak discharge for unregulated rural and urban watersheds. These techniques should be useful to engineers and hydrologists for planning and design applications. This report summarizes the statewide regression equations for rural watersheds in each State, summarizes the applicable metropolitan area or statewide regression equations for urban watersheds, describes the National Flood Frequency Program for making these computations, and provides much of the reference information on the extrapolation variables needed to run the program.

Selecting risk factors: a comparison of discriminant analysis, logistic regression and Cox's regression model using data from the Tromsø Heart Study.

PubMed

Brenn, T; Arnesen, E

1985-01-01

For comparative evaluation, discriminant analysis, logistic regression and Cox's model were used to select risk factors for total and coronary deaths among 6595 men aged 20-49 followed for 9 years. Groups with mortality between 5 and 93 per 1000 were considered. Discriminant analysis selected variable sets only marginally different from the logistic and Cox methods which always selected the same sets. A time-saving option, offered for both the logistic and Cox selection, showed no advantage compared with discriminant analysis. Analysing more than 3800 subjects, the logistic and Cox methods consumed, respectively, 80 and 10 times more computer time than discriminant analysis. When including the same set of variables in non-stepwise analyses, all methods estimated coefficients that in most cases were almost identical. In conclusion, discriminant analysis is advocated for preliminary or stepwise analysis, otherwise Cox's method should be used.

Modification of the Mantel-Haenszel and Logistic Regression DIF Procedures to Incorporate the SIBTEST Regression Correction

ERIC Educational Resources Information Center

DeMars, Christine E.

2009-01-01

The Mantel-Haenszel (MH) and logistic regression (LR) differential item functioning (DIF) procedures have inflated Type I error rates when there are large mean group differences, short tests, and large sample sizes.When there are large group differences in mean score, groups matched on the observed number-correct score differ on true score,…

Satellite rainfall retrieval by logistic regression

NASA Technical Reports Server (NTRS)

Chiu, Long S.

1986-01-01

The potential use of logistic regression in rainfall estimation from satellite measurements is investigated. Satellite measurements provide covariate information in terms of radiances from different remote sensors.The logistic regression technique can effectively accommodate many covariates and test their significance in the estimation. The outcome from the logistical model is the probability that the rainrate of a satellite pixel is above a certain threshold. By varying the thresholds, a rainrate histogram can be obtained, from which the mean and the variant can be estimated. A logistical model is developed and applied to rainfall data collected during GATE, using as covariates the fractional rain area and a radiance measurement which is deduced from a microwave temperature-rainrate relation. It is demonstrated that the fractional rain area is an important covariate in the model, consistent with the use of the so-called Area Time Integral in estimating total rain volume in other studies. To calibrate the logistical model, simulated rain fields generated by rainfield models with prescribed parameters are needed. A stringent test of the logistical model is its ability to recover the prescribed parameters of simulated rain fields. A rain field simulation model which preserves the fractional rain area and lognormality of rainrates as found in GATE is developed. A stochastic regression model of branching and immigration whose solutions are lognormally distributed in some asymptotic limits has also been developed.

Practical Session: Logistic Regression

NASA Astrophysics Data System (ADS)

Clausel, M.; Grégoire, G.

2014-12-01

An exercise is proposed to illustrate the logistic regression. One investigates the different risk factors in the apparition of coronary heart disease. It has been proposed in Chapter 5 of the book of D.G. Kleinbaum and M. Klein, "Logistic Regression", Statistics for Biology and Health, Springer Science Business Media, LLC (2010) and also by D. Chessel and A.B. Dufour in Lyon 1 (see Sect. 6 of http://pbil.univ-lyon1.fr/R/pdf/tdr341.pdf). This example is based on data given in the file evans.txt coming from http://www.sph.emory.edu/dkleinb/logreg3.htm#data.

The cross-validated AUC for MCP-logistic regression with high-dimensional data.

PubMed

Jiang, Dingfeng; Huang, Jian; Zhang, Ying

2013-10-01

We propose a cross-validated area under the receiving operator characteristic (ROC) curve (CV-AUC) criterion for tuning parameter selection for penalized methods in sparse, high-dimensional logistic regression models. We use this criterion in combination with the minimax concave penalty (MCP) method for variable selection. The CV-AUC criterion is specifically designed for optimizing the classification performance for binary outcome data. To implement the proposed approach, we derive an efficient coordinate descent algorithm to compute the MCP-logistic regression solution surface. Simulation studies are conducted to evaluate the finite sample performance of the proposed method and its comparison with the existing methods including the Akaike information criterion (AIC), Bayesian information criterion (BIC) or Extended BIC (EBIC). The model selected based on the CV-AUC criterion tends to have a larger predictive AUC and smaller classification error than those with tuning parameters selected using the AIC, BIC or EBIC. We illustrate the application of the MCP-logistic regression with the CV-AUC criterion on three microarray datasets from the studies that attempt to identify genes related to cancers. Our simulation studies and data examples demonstrate that the CV-AUC is an attractive method for tuning parameter selection for penalized methods in high-dimensional logistic regression models.

Methods for estimating selected spring and fall low-flow frequency statistics for ungaged stream sites in Iowa, based on data through June 2014

USGS Publications Warehouse

Eash, David A.; Barnes, Kimberlee K.; O'Shea, Padraic S.

2016-09-19

A statewide study was led to develop regression equations for estimating three selected spring and three selected fall low-flow frequency statistics for ungaged stream sites in Iowa. The estimation equations developed for the six low-flow frequency statistics include spring (April through June) 1-, 7-, and 30-day mean low flows for a recurrence interval of 10 years and fall (October through December) 1-, 7-, and 30-day mean low flows for a recurrence interval of 10 years. Estimates of the three selected spring statistics are provided for 241 U.S. Geological Survey continuous-record streamgages, and estimates of the three selected fall statistics are provided for 238 of these streamgages, using data through June 2014. Because only 9 years of fall streamflow record were available, three streamgages included in the development of the spring regression equations were not included in the development of the fall regression equations. Because of regulation, diversion, or urbanization, 30 of the 241 streamgages were not included in the development of the regression equations. The study area includes Iowa and adjacent areas within 50 miles of the Iowa border. Because trend analyses indicated statistically significant positive trends when considering the period of record for most of the streamgages, the longest, most recent period of record without a significant trend was determined for each streamgage for use in the study. Geographic information system software was used to measure 63 selected basin characteristics for each of the 211streamgages used to develop the regional regression equations. The study area was divided into three low-flow regions that were defined in a previous study for the development of regional regression equations.Because several streamgages included in the development of regional regression equations have estimates of zero flow calculated from observed streamflow for selected spring and fall low-flow frequency statistics, the final equations for the three low-flow regions were developed using two types of regression analyses—left-censored and generalized-least-squares regression analyses. A total of 211 streamgages were included in the development of nine spring regression equations—three equations for each of the three low-flow regions. A total of 208 streamgages were included in the development of nine fall regression equations—three equations for each of the three low-flow regions. A censoring threshold was used to develop 15 left-censored regression equations to estimate the three fall low-flow frequency statistics for each of the three low-flow regions and to estimate the three spring low-flow frequency statistics for the southern and northwest regions. For the northeast region, generalized-least-squares regression was used to develop three equations to estimate the three spring low-flow frequency statistics. For the northeast region, average standard errors of prediction range from 32.4 to 48.4 percent for the spring equations and average standard errors of estimate range from 56.4 to 73.8 percent for the fall equations. For the northwest region, average standard errors of estimate range from 58.9 to 62.1 percent for the spring equations and from 83.2 to 109.4 percent for the fall equations. For the southern region, average standard errors of estimate range from 43.2 to 64.0 percent for the spring equations and from 78.1 to 78.7 percent for the fall equations.The regression equations are applicable only to stream sites in Iowa with low flows not substantially affected by regulation, diversion, or urbanization and with basin characteristics within the range of those used to develop the equations. The regression equations will be implemented within the U.S. Geological Survey StreamStats Web-based geographic information system application. StreamStats allows users to click on any ungaged stream site and compute estimates of the six selected spring and fall low-flow statistics; in addition, 90-percent prediction intervals and the measured basin characteristics for the ungaged site are provided. StreamStats also allows users to click on any Iowa streamgage to obtain computed estimates for the six selected spring and fall low-flow statistics.

Impact of national smoke-free legislation on home smoking bans: findings from the International Tobacco Control Policy Evaluation Project Europe Surveys.

PubMed

Mons, Ute; Nagelhout, Gera E; Allwright, Shane; Guignard, Romain; van den Putte, Bas; Willemsen, Marc C; Fong, Geoffrey T; Brenner, Hermann; Pötschke-Langer, Martina; Breitling, Lutz P

2013-05-01

To measure changes in prevalence and predictors of home smoking bans (HSBs) among smokers in four European countries after the implementation of national smoke-free legislation. Two waves of the International Tobacco Control Policy Evaluation Project Europe Surveys, which is a prospective panel study. Pre- and post-legislation data were used from Ireland, France, Germany and the Netherlands. Two pre-legislation waves from the UK were used as control. 4634 respondents from the intervention countries and 1080 from the control country completed both baseline and follow-up and were included in the present analyses. Multiple logistic regression models to identify predictors of having or of adopting a total HSB, and Generalised Estimating Equation models to compare patterns of change after implementation of smoke-free legislation to a control country without such legislation. Most smokers had at least partial smoking restrictions in their home, but the proportions varied significantly between countries. After implementation of national smoke-free legislation, the proportion of smokers with a total HSB increased significantly in all four countries. Among continuing smokers, the number of cigarettes smoked per day either remained stable or decreased significantly. Multiple logistic regression models indicated that having a young child in the household and supporting smoking bans in bars were important correlates of having a pre-legislation HSB. Prospective predictors of imposing a HSB between survey waves were planning to quit smoking, supporting a total smoking ban in bars and the birth of a child. Generalised Estimating Equation models indicated that the change in total HSB in the intervention countries was greater than that in the control country. The findings suggest that smoke-free legislation does not lead to more smoking in smokers' homes. On the contrary, our findings demonstrate that smoke-free legislation may stimulate smokers to establish total smoking bans in their homes.

Infant Formula Feeding at Birth Is Common and Inversely Associated with Subsequent Breastfeeding Behavior in Vietnam123

PubMed Central

Nguyen, Tuan T; Withers, Mellissa; Hajeebhoy, Nemat; Frongillo, Edward A

2016-01-01

Background: The association between infant formula feeding at birth and subsequent feeding patterns in a low- or middle-income context is not clear. Objective: We examined the association of infant formula feeding during the first 3 d after birth with subsequent infant formula feeding and early breastfeeding cessation in Vietnam. Methods: In a cross-sectional survey, we interviewed 10,681 mothers with children aged 0−23 mo (mean age: 8.2 mo; 52% boys) about their feeding practices during the first 3 d after birth and on the previous day. We used stratified analysis, multiple logistic regression, propensity score-matching analysis, and structural equation modeling to minimize the limitation of the cross-sectional design and to ensure the consistency of the findings. Results: Infant formula feeding during the first 3 d after birth (50%) was associated with a higher prevalence of subsequent infant formula feeding [stratified analysis: 7−28% higher (nonoverlapping 95% CIs for most comparisons); propensity score-matching analysis: 13% higher (P < 0.001); multiple logistic regression: OR: 1.47 (95% CI: 1.30, 1.67)]. This practice was also associated with a higher prevalence of early breastfeeding cessation (e.g., <24 mo) [propensity score-matching analysis: 2% (P = 0.08); OR: 1.33 (95% CI: 1.12, 1.59)]. Structural equation modeling showed that infant formula feeding during the first 3 d after birth was associated with a higher prevalence of subsequent infant formula feeding (β: 0.244; P < 0.001), which in turn was linked to early breastfeeding cessation (β: 0.285; P < 0.001). Conclusions: Infant formula feeding during the first 3 d after birth was associated with increased subsequent infant formula feeding and the early cessation of breastfeeding, which underscores the need to make early, exclusive breastfeeding normative and to create environments that support it. PMID:27605404

Factors related to the joint probability of flooding on paired streams

USGS Publications Warehouse

Koltun, G.F.; Sherwood, J.M.

1998-01-01

The factors related to the joint probabilty of flooding on paired streams were investigated and quantified to provide information to aid in the design of hydraulic structures where the joint probabilty of flooding is an element of the design criteria. Stream pairs were considered to have flooded jointly at the design-year flood threshold (corresponding to the 2-, 10-, 25-, or 50-year instantaneous peak streamflow) if peak streamflows at both streams in the pair were observed or predicted to have equaled or exceeded the threshold on a given calendar day. Daily mean streamflow data were used as a substitute for instantaneous peak streamflow data to determine which flood thresholds were equaled or exceeded on any given day. Instantaneous peak streamflow data, when available, were used preferentially to assess flood-threshold exceedance. Daily mean streamflow data for each stream were paired with concurrent daily mean streamflow data at the other streams. Observed probabilities of joint flooding, determined for the 2-, 10-, 25-, and 50-year flood thresholds, were computed as the ratios of the total number of days when streamflows at both streams concurrently equaled or exceeded their flood thresholds (events) to the total number of days where streamflows at either stream equaled or exceeded its flood threshold (trials). A combination of correlation analyses, graphical analyses, and logistic-regression analyses were used to identify and quantify factors associated with the observed probabilities of joint flooding (event-trial ratios). The analyses indicated that the distance between drainage area centroids, the ratio of the smaller to larger drainage area, the mean drainage area, and the centroid angle adjusted 30 degrees were the basin characteristics most closely associated with the joint probabilty of flooding on paired streams in Ohio. In general, the analyses indicated that the joint probabilty of flooding decreases with an increase in centroid distance and increases with increases in drainage area ratio, mean drainage area, and centroid angle adjusted 30 degrees. Logistic-regression equations were developed, which can be used to estimate the probability that streamflows at two streams jointly equal or exceed the 2-year flood threshold given that the streamflow at one of the two streams equals or exceeds the 2-year flood threshold. The logistic-regression equations are applicable to stream pairs in Ohio (and border areas of adjacent states) that are unregulated, free of significant urban influences, and have characteristics similar to those of the 304 gaged stream pairs used in the logistic-regression analyses. Contingency tables were constructed and analyzed to provide information about the bivariate distribution of floods on paired streams. The contingency tables showed that the percentage of trials in which both streams in the pair concurrently flood at identical recurrence-interval ranges generally increased as centroid distances decreased and was greatest for stream pairs with adjusted centroid angles greater than or equal to 60 degrees and drainage area ratios greater than or equal to 0.01. Also, as centroid distance increased, streamflow at one stream in the pair was more likely to be in a less than 2-year recurrence-interval range when streamflow at the second stream was in a 2-year or greater recurrence-interval range.

Prediction of Advisability of Returning Home Using the Home Care Score

PubMed Central

Matsugi, Akiyoshi; Tani, Keisuke; Tamaru, Yoshiki; Yoshioka, Nami; Yamashita, Akira; Mori, Nobuhiko; Oku, Kosuke; Ikeda, Masashi; Nagano, Kiyoshi

2015-01-01

Purpose. The aim of this study was to assess whether the home care score (HCS), which was developed by the Ministry of Health and Welfare in Japan in 1992, is useful for the prediction of advisability of home care. Methods. Subjects living at home and in assisted-living facilities were analyzed. Binominal logistic regression analyses, using age, sex, the functional independence measure score, and the HCS, along with receiver operating characteristic curve analyses, were conducted. Findings/Conclusions. Only HCS was selected for the regression equation. Receiver operating characteristic curve analysis revealed that the area under the curve (0.9), sensitivity (0.82), specificity (0.83), and positive predictive value (0.84) for HCS were higher than those for the functional independence measure, indicating that the HCS is a powerful predictor for advisability of home care. Clinical Relevance. Comprehensive measurements of the condition of provided care and the activities of daily living of the subjects, which are included in the HCS, are required for the prediction of advisability of home care. PMID:26491568

A simple approach to power and sample size calculations in logistic regression and Cox regression models.

PubMed

Vaeth, Michael; Skovlund, Eva

2004-06-15

For a given regression problem it is possible to identify a suitably defined equivalent two-sample problem such that the power or sample size obtained for the two-sample problem also applies to the regression problem. For a standard linear regression model the equivalent two-sample problem is easily identified, but for generalized linear models and for Cox regression models the situation is more complicated. An approximately equivalent two-sample problem may, however, also be identified here. In particular, we show that for logistic regression and Cox regression models the equivalent two-sample problem is obtained by selecting two equally sized samples for which the parameters differ by a value equal to the slope times twice the standard deviation of the independent variable and further requiring that the overall expected number of events is unchanged. In a simulation study we examine the validity of this approach to power calculations in logistic regression and Cox regression models. Several different covariate distributions are considered for selected values of the overall response probability and a range of alternatives. For the Cox regression model we consider both constant and non-constant hazard rates. The results show that in general the approach is remarkably accurate even in relatively small samples. Some discrepancies are, however, found in small samples with few events and a highly skewed covariate distribution. Comparison with results based on alternative methods for logistic regression models with a single continuous covariate indicates that the proposed method is at least as good as its competitors. The method is easy to implement and therefore provides a simple way to extend the range of problems that can be covered by the usual formulas for power and sample size determination. Copyright 2004 John Wiley & Sons, Ltd.

Developing prediction equations and a mobile phone application to identify infants at risk of obesity.

PubMed

Santorelli, Gillian; Petherick, Emily S; Wright, John; Wilson, Brad; Samiei, Haider; Cameron, Noël; Johnson, William

2013-01-01

Advancements in knowledge of obesity aetiology and mobile phone technology have created the opportunity to develop an electronic tool to predict an infant's risk of childhood obesity. The study aims were to develop and validate equations for the prediction of childhood obesity and integrate them into a mobile phone application (App). Anthropometry and childhood obesity risk data were obtained for 1868 UK-born White or South Asian infants in the Born in Bradford cohort. Logistic regression was used to develop prediction equations (at 6 ± 1.5, 9 ± 1.5 and 12 ± 1.5 months) for risk of childhood obesity (BMI at 2 years >91(st) centile and weight gain from 0-2 years >1 centile band) incorporating sex, birth weight, and weight gain as predictors. The discrimination accuracy of the equations was assessed by the area under the curve (AUC); internal validity by comparing area under the curve to those obtained in bootstrapped samples; and external validity by applying the equations to an external sample. An App was built to incorporate six final equations (two at each age, one of which included maternal BMI). The equations had good discrimination (AUCs 86-91%), with the addition of maternal BMI marginally improving prediction. The AUCs in the bootstrapped and external validation samples were similar to those obtained in the development sample. The App is user-friendly, requires a minimum amount of information, and provides a risk assessment of low, medium, or high accompanied by advice and website links to government recommendations. Prediction equations for risk of childhood obesity have been developed and incorporated into a novel App, thereby providing proof of concept that childhood obesity prediction research can be integrated with advancements in technology.

Prostate Cancer Predictive Simulation Modelling, Assessing the Risk Technique (PCP-SMART): Introduction and Initial Clinical Efficacy Evaluation Data Presentation of a Simple Novel Mathematical Simulation Modelling Method, Devised to Predict the Outcome of Prostate Biopsy on an Individual Basis.

PubMed

Spyropoulos, Evangelos; Kotsiris, Dimitrios; Spyropoulos, Katherine; Panagopoulos, Aggelos; Galanakis, Ioannis; Mavrikos, Stamatios

2017-02-01

We developed a mathematical "prostate cancer (PCa) conditions simulating" predictive model (PCP-SMART), from which we derived a novel PCa predictor (prostate cancer risk determinator [PCRD] index) and a PCa risk equation. We used these to estimate the probability of finding PCa on prostate biopsy, on an individual basis. A total of 371 men who had undergone transrectal ultrasound-guided prostate biopsy were enrolled in the present study. Given that PCa risk relates to the total prostate-specific antigen (tPSA) level, age, prostate volume, free PSA (fPSA), fPSA/tPSA ratio, and PSA density and that tPSA ≥ 50 ng/mL has a 98.5% positive predictive value for a PCa diagnosis, we hypothesized that correlating 2 variables composed of 3 ratios (1, tPSA/age; 2, tPSA/prostate volume; and 3, fPSA/tPSA; 1 variable including the patient's tPSA and the other, a tPSA value of 50 ng/mL) could operate as a PCa conditions imitating/simulating model. Linear regression analysis was used to derive the coefficient of determination (R 2 ), termed the PCRD index. To estimate the PCRD index's predictive validity, we used the χ 2 test, multiple logistic regression analysis with PCa risk equation formation, calculation of test performance characteristics, and area under the receiver operating characteristic curve analysis using SPSS, version 22 (P < .05). The biopsy findings were positive for PCa in 167 patients (45.1%) and negative in 164 (44.2%). The PCRD index was positively signed in 89.82% positive PCa cases and negative in 91.46% negative PCa cases (χ 2 test; P < .001; relative risk, 8.98). The sensitivity was 89.8%, specificity was 91.5%, positive predictive value was 91.5%, negative predictive value was 89.8%, positive likelihood ratio was 10.5, negative likelihood ratio was 0.11, and accuracy was 90.6%. Multiple logistic regression revealed the PCRD index as an independent PCa predictor, and the formulated risk equation was 91% accurate in predicting the probability of finding PCa. On the receiver operating characteristic analysis, the PCRD index (area under the curve, 0.926) significantly (P < .001) outperformed other, established PCa predictors. The PCRD index effectively predicted the prostate biopsy outcome, correctly identifying 9 of 10 men who were eventually diagnosed with PCa and correctly ruling out PCa for 9 of 10 men who did not have PCa. Its predictive power significantly outperformed established PCa predictors, and the formulated risk equation accurately calculated the probability of finding cancer on biopsy, on an individual patient basis. Copyright © 2016 Elsevier Inc. All rights reserved.

Peak flow regression equations For small, ungaged streams in Maine: Comparing map-based to field-based variables

USGS Publications Warehouse

Lombard, Pamela J.; Hodgkins, Glenn A.

2015-01-01

Regression equations to estimate peak streamflows with 1- to 500-year recurrence intervals (annual exceedance probabilities from 99 to 0.2 percent, respectively) were developed for small, ungaged streams in Maine. Equations presented here are the best available equations for estimating peak flows at ungaged basins in Maine with drainage areas from 0.3 to 12 square miles (mi2). Previously developed equations continue to be the best available equations for estimating peak flows for basin areas greater than 12 mi2. New equations presented here are based on streamflow records at 40 U.S. Geological Survey streamgages with a minimum of 10 years of recorded peak flows between 1963 and 2012. Ordinary least-squares regression techniques were used to determine the best explanatory variables for the regression equations. Traditional map-based explanatory variables were compared to variables requiring field measurements. Two field-based variables—culvert rust lines and bankfull channel widths—either were not commonly found or did not explain enough of the variability in the peak flows to warrant inclusion in the equations. The best explanatory variables were drainage area and percent basin wetlands; values for these variables were determined with a geographic information system. Generalized least-squares regression was used with these two variables to determine the equation coefficients and estimates of accuracy for the final equations.

Robust logistic regression to narrow down the winner's curse for rare and recessive susceptibility variants.

PubMed

Kesselmeier, Miriam; Lorenzo Bermejo, Justo

2017-11-01

Logistic regression is the most common technique used for genetic case-control association studies. A disadvantage of standard maximum likelihood estimators of the genotype relative risk (GRR) is their strong dependence on outlier subjects, for example, patients diagnosed at unusually young age. Robust methods are available to constrain outlier influence, but they are scarcely used in genetic studies. This article provides a non-intimidating introduction to robust logistic regression, and investigates its benefits and limitations in genetic association studies. We applied the bounded Huber and extended the R package 'robustbase' with the re-descending Hampel functions to down-weight outlier influence. Computer simulations were carried out to assess the type I error rate, mean squared error (MSE) and statistical power according to major characteristics of the genetic study and investigated markers. Simulations were complemented with the analysis of real data. Both standard and robust estimation controlled type I error rates. Standard logistic regression showed the highest power but standard GRR estimates also showed the largest bias and MSE, in particular for associated rare and recessive variants. For illustration, a recessive variant with a true GRR=6.32 and a minor allele frequency=0.05 investigated in a 1000 case/1000 control study by standard logistic regression resulted in power=0.60 and MSE=16.5. The corresponding figures for Huber-based estimation were power=0.51 and MSE=0.53. Overall, Hampel- and Huber-based GRR estimates did not differ much. Robust logistic regression may represent a valuable alternative to standard maximum likelihood estimation when the focus lies on risk prediction rather than identification of susceptibility variants. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

CUSUM-Logistic Regression analysis for the rapid detection of errors in clinical laboratory test results.

PubMed

Sampson, Maureen L; Gounden, Verena; van Deventer, Hendrik E; Remaley, Alan T

2016-02-01

The main drawback of the periodic analysis of quality control (QC) material is that test performance is not monitored in time periods between QC analyses, potentially leading to the reporting of faulty test results. The objective of this study was to develop a patient based QC procedure for the more timely detection of test errors. Results from a Chem-14 panel measured on the Beckman LX20 analyzer were used to develop the model. Each test result was predicted from the other 13 members of the panel by multiple regression, which resulted in correlation coefficients between the predicted and measured result of >0.7 for 8 of the 14 tests. A logistic regression model, which utilized the measured test result, the predicted test result, the day of the week and time of day, was then developed for predicting test errors. The output of the logistic regression was tallied by a daily CUSUM approach and used to predict test errors, with a fixed specificity of 90%. The mean average run length (ARL) before error detection by CUSUM-Logistic Regression (CSLR) was 20 with a mean sensitivity of 97%, which was considerably shorter than the mean ARL of 53 (sensitivity 87.5%) for a simple prediction model that only used the measured result for error detection. A CUSUM-Logistic Regression analysis of patient laboratory data can be an effective approach for the rapid and sensitive detection of clinical laboratory errors. Published by Elsevier Inc.

Methods for estimating the magnitude and frequency of peak streamflows for unregulated streams in Oklahoma

USGS Publications Warehouse

Lewis, Jason M.

2010-01-01

Peak-streamflow regression equations were determined for estimating flows with exceedance probabilities from 50 to 0.2 percent for the state of Oklahoma. These regression equations incorporate basin characteristics to estimate peak-streamflow magnitude and frequency throughout the state by use of a generalized least squares regression analysis. The most statistically significant independent variables required to estimate peak-streamflow magnitude and frequency for unregulated streams in Oklahoma are contributing drainage area, mean-annual precipitation, and main-channel slope. The regression equations are applicable for watershed basins with drainage areas less than 2,510 square miles that are not affected by regulation. The resulting regression equations had a standard model error ranging from 31 to 46 percent. Annual-maximum peak flows observed at 231 streamflow-gaging stations through water year 2008 were used for the regression analysis. Gage peak-streamflow estimates were used from previous work unless 2008 gaging-station data were available, in which new peak-streamflow estimates were calculated. The U.S. Geological Survey StreamStats web application was used to obtain the independent variables required for the peak-streamflow regression equations. Limitations on the use of the regression equations and the reliability of regression estimates for natural unregulated streams are described. Log-Pearson Type III analysis information, basin and climate characteristics, and the peak-streamflow frequency estimates for the 231 gaging stations in and near Oklahoma are listed. Methodologies are presented to estimate peak streamflows at ungaged sites by using estimates from gaging stations on unregulated streams. For ungaged sites on urban streams and streams regulated by small floodwater retarding structures, an adjustment of the statewide regression equations for natural unregulated streams can be used to estimate peak-streamflow magnitude and frequency.

Nonconvex Sparse Logistic Regression With Weakly Convex Regularization

NASA Astrophysics Data System (ADS)

Shen, Xinyue; Gu, Yuantao

2018-06-01

In this work we propose to fit a sparse logistic regression model by a weakly convex regularized nonconvex optimization problem. The idea is based on the finding that a weakly convex function as an approximation of the $\\ell_0$ pseudo norm is able to better induce sparsity than the commonly used $\\ell_1$ norm. For a class of weakly convex sparsity inducing functions, we prove the nonconvexity of the corresponding sparse logistic regression problem, and study its local optimality conditions and the choice of the regularization parameter to exclude trivial solutions. Despite the nonconvexity, a method based on proximal gradient descent is used to solve the general weakly convex sparse logistic regression, and its convergence behavior is studied theoretically. Then the general framework is applied to a specific weakly convex function, and a necessary and sufficient local optimality condition is provided. The solution method is instantiated in this case as an iterative firm-shrinkage algorithm, and its effectiveness is demonstrated in numerical experiments by both randomly generated and real datasets.

A comparative study on entrepreneurial attitudes modeled with logistic regression and Bayes nets.

PubMed

López Puga, Jorge; García García, Juan

2012-11-01

Entrepreneurship research is receiving increasing attention in our context, as entrepreneurs are key social agents involved in economic development. We compare the success of the dichotomic logistic regression model and the Bayes simple classifier to predict entrepreneurship, after manipulating the percentage of missing data and the level of categorization in predictors. A sample of undergraduate university students (N = 1230) completed five scales (motivation, attitude towards business creation, obstacles, deficiencies, and training needs) and we found that each of them predicted different aspects of the tendency to business creation. Additionally, our results show that the receiver operating characteristic (ROC) curve is affected by the rate of missing data in both techniques, but logistic regression seems to be more vulnerable when faced with missing data, whereas Bayes nets underperform slightly when categorization has been manipulated. Our study sheds light on the potential entrepreneur profile and we propose to use Bayesian networks as an additional alternative to overcome the weaknesses of logistic regression when missing data are present in applied research.

Epidemiologic programs for computers and calculators. A microcomputer program for multiple logistic regression by unconditional and conditional maximum likelihood methods.

PubMed

Campos-Filho, N; Franco, E L

1989-02-01

A frequent procedure in matched case-control studies is to report results from the multivariate unmatched analyses if they do not differ substantially from the ones obtained after conditioning on the matching variables. Although conceptually simple, this rule requires that an extensive series of logistic regression models be evaluated by both the conditional and unconditional maximum likelihood methods. Most computer programs for logistic regression employ only one maximum likelihood method, which requires that the analyses be performed in separate steps. This paper describes a Pascal microcomputer (IBM PC) program that performs multiple logistic regression by both maximum likelihood estimation methods, which obviates the need for switching between programs to obtain relative risk estimates from both matched and unmatched analyses. The program calculates most standard statistics and allows factoring of categorical or continuous variables by two distinct methods of contrast. A built-in, descriptive statistics option allows the user to inspect the distribution of cases and controls across categories of any given variable.

Comparison of cranial sex determination by discriminant analysis and logistic regression.

PubMed

Amores-Ampuero, Anabel; Alemán, Inmaculada

2016-04-05

Various methods have been proposed for estimating dimorphism. The objective of this study was to compare sex determination results from cranial measurements using discriminant analysis or logistic regression. The study sample comprised 130 individuals (70 males) of known sex, age, and cause of death from San José cemetery in Granada (Spain). Measurements of 19 neurocranial dimensions and 11 splanchnocranial dimensions were subjected to discriminant analysis and logistic regression, and the percentages of correct classification were compared between the sex functions obtained with each method. The discriminant capacity of the selected variables was evaluated with a cross-validation procedure. The percentage accuracy with discriminant analysis was 78.2% for the neurocranium (82.4% in females and 74.6% in males) and 73.7% for the splanchnocranium (79.6% in females and 68.8% in males). These percentages were higher with logistic regression analysis: 85.7% for the neurocranium (in both sexes) and 94.1% for the splanchnocranium (100% in females and 91.7% in males).

Stepwise Distributed Open Innovation Contests for Software Development: Acceleration of Genome-Wide Association Analysis

PubMed Central

Hill, Andrew; Loh, Po-Ru; Bharadwaj, Ragu B.; Pons, Pascal; Shang, Jingbo; Guinan, Eva; Lakhani, Karim; Kilty, Iain

2017-01-01

Abstract Background: The association of differing genotypes with disease-related phenotypic traits offers great potential to both help identify new therapeutic targets and support stratification of patients who would gain the greatest benefit from specific drug classes. Development of low-cost genotyping and sequencing has made collecting large-scale genotyping data routine in population and therapeutic intervention studies. In addition, a range of new technologies is being used to capture numerous new and complex phenotypic descriptors. As a result, genotype and phenotype datasets have grown exponentially. Genome-wide association studies associate genotypes and phenotypes using methods such as logistic regression. As existing tools for association analysis limit the efficiency by which value can be extracted from increasing volumes of data, there is a pressing need for new software tools that can accelerate association analyses on large genotype-phenotype datasets. Results: Using open innovation (OI) and contest-based crowdsourcing, the logistic regression analysis in a leading, community-standard genetics software package (PLINK 1.07) was substantially accelerated. OI allowed us to do this in <6 months by providing rapid access to highly skilled programmers with specialized, difficult-to-find skill sets. Through a crowd-based contest a combination of computational, numeric, and algorithmic approaches was identified that accelerated the logistic regression in PLINK 1.07 by 18- to 45-fold. Combining contest-derived logistic regression code with coarse-grained parallelization, multithreading, and associated changes to data initialization code further developed through distributed innovation, we achieved an end-to-end speedup of 591-fold for a data set size of 6678 subjects by 645 863 variants, compared to PLINK 1.07's logistic regression. This represents a reduction in run time from 4.8 hours to 29 seconds. Accelerated logistic regression code developed in this project has been incorporated into the PLINK2 project. Conclusions: Using iterative competition-based OI, we have developed a new, faster implementation of logistic regression for genome-wide association studies analysis. We present lessons learned and recommendations on running a successful OI process for bioinformatics. PMID:28327993

Stepwise Distributed Open Innovation Contests for Software Development: Acceleration of Genome-Wide Association Analysis.

PubMed

Hill, Andrew; Loh, Po-Ru; Bharadwaj, Ragu B; Pons, Pascal; Shang, Jingbo; Guinan, Eva; Lakhani, Karim; Kilty, Iain; Jelinsky, Scott A

2017-05-01

The association of differing genotypes with disease-related phenotypic traits offers great potential to both help identify new therapeutic targets and support stratification of patients who would gain the greatest benefit from specific drug classes. Development of low-cost genotyping and sequencing has made collecting large-scale genotyping data routine in population and therapeutic intervention studies. In addition, a range of new technologies is being used to capture numerous new and complex phenotypic descriptors. As a result, genotype and phenotype datasets have grown exponentially. Genome-wide association studies associate genotypes and phenotypes using methods such as logistic regression. As existing tools for association analysis limit the efficiency by which value can be extracted from increasing volumes of data, there is a pressing need for new software tools that can accelerate association analyses on large genotype-phenotype datasets. Using open innovation (OI) and contest-based crowdsourcing, the logistic regression analysis in a leading, community-standard genetics software package (PLINK 1.07) was substantially accelerated. OI allowed us to do this in <6 months by providing rapid access to highly skilled programmers with specialized, difficult-to-find skill sets. Through a crowd-based contest a combination of computational, numeric, and algorithmic approaches was identified that accelerated the logistic regression in PLINK 1.07 by 18- to 45-fold. Combining contest-derived logistic regression code with coarse-grained parallelization, multithreading, and associated changes to data initialization code further developed through distributed innovation, we achieved an end-to-end speedup of 591-fold for a data set size of 6678 subjects by 645 863 variants, compared to PLINK 1.07's logistic regression. This represents a reduction in run time from 4.8 hours to 29 seconds. Accelerated logistic regression code developed in this project has been incorporated into the PLINK2 project. Using iterative competition-based OI, we have developed a new, faster implementation of logistic regression for genome-wide association studies analysis. We present lessons learned and recommendations on running a successful OI process for bioinformatics. © The Author 2017. Published by Oxford University Press.

Easy and low-cost identification of metabolic syndrome in patients treated with second-generation antipsychotics: artificial neural network and logistic regression models.

PubMed

Lin, Chao-Cheng; Bai, Ya-Mei; Chen, Jen-Yeu; Hwang, Tzung-Jeng; Chen, Tzu-Ting; Chiu, Hung-Wen; Li, Yu-Chuan

2010-03-01

Metabolic syndrome (MetS) is an important side effect of second-generation antipsychotics (SGAs). However, many SGA-treated patients with MetS remain undetected. In this study, we trained and validated artificial neural network (ANN) and multiple logistic regression models without biochemical parameters to rapidly identify MetS in patients with SGA treatment. A total of 383 patients with a diagnosis of schizophrenia or schizoaffective disorder (DSM-IV criteria) with SGA treatment for more than 6 months were investigated to determine whether they met the MetS criteria according to the International Diabetes Federation. The data for these patients were collected between March 2005 and September 2005. The input variables of ANN and logistic regression were limited to demographic and anthropometric data only. All models were trained by randomly selecting two-thirds of the patient data and were internally validated with the remaining one-third of the data. The models were then externally validated with data from 69 patients from another hospital, collected between March 2008 and June 2008. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of all models. Both the final ANN and logistic regression models had high accuracy (88.3% vs 83.6%), sensitivity (93.1% vs 86.2%), and specificity (86.9% vs 83.8%) to identify MetS in the internal validation set. The mean +/- SD AUC was high for both the ANN and logistic regression models (0.934 +/- 0.033 vs 0.922 +/- 0.035, P = .63). During external validation, high AUC was still obtained for both models. Waist circumference and diastolic blood pressure were the common variables that were left in the final ANN and logistic regression models. Our study developed accurate ANN and logistic regression models to detect MetS in patients with SGA treatment. The models are likely to provide a noninvasive tool for large-scale screening of MetS in this group of patients. (c) 2010 Physicians Postgraduate Press, Inc.

Bayesian logistic regression in detection of gene-steroid interaction for cancer at PDLIM5 locus.

PubMed

Wang, Ke-Sheng; Owusu, Daniel; Pan, Yue; Xie, Changchun

2016-06-01

The PDZ and LIM domain 5 (PDLIM5) gene may play a role in cancer, bipolar disorder, major depression, alcohol dependence and schizophrenia; however, little is known about the interaction effect of steroid and PDLIM5 gene on cancer. This study examined 47 single-nucleotide polymorphisms (SNPs) within the PDLIM5 gene in the Marshfield sample with 716 cancer patients (any diagnosed cancer, excluding minor skin cancer) and 2848 noncancer controls. Multiple logistic regression model in PLINK software was used to examine the association of each SNP with cancer. Bayesian logistic regression in PROC GENMOD in SAS statistical software, ver. 9.4 was used to detect gene- steroid interactions influencing cancer. Single marker analysis using PLINK identified 12 SNPs associated with cancer (P< 0.05); especially, SNP rs6532496 revealed the strongest association with cancer (P = 6.84 × 10⁻³); while the next best signal was rs951613 (P = 7.46 × 10⁻³). Classic logistic regression in PROC GENMOD showed that both rs6532496 and rs951613 revealed strong gene-steroid interaction effects (OR=2.18, 95% CI=1.31-3.63 with P = 2.9 × 10⁻³ for rs6532496 and OR=2.07, 95% CI=1.24-3.45 with P = 5.43 × 10⁻³ for rs951613, respectively). Results from Bayesian logistic regression showed stronger interaction effects (OR=2.26, 95% CI=1.2-3.38 for rs6532496 and OR=2.14, 95% CI=1.14-3.2 for rs951613, respectively). All the 12 SNPs associated with cancer revealed significant gene-steroid interaction effects (P < 0.05); whereas 13 SNPs showed gene-steroid interaction effects without main effect on cancer. SNP rs4634230 revealed the strongest gene-steroid interaction effect (OR=2.49, 95% CI=1.5-4.13 with P = 4.0 × 10⁻⁴ based on the classic logistic regression and OR=2.59, 95% CI=1.4-3.97 from Bayesian logistic regression; respectively). This study provides evidence of common genetic variants within the PDLIM5 gene and interactions between PLDIM5 gene polymorphisms and steroid use influencing cancer.

[Development of competency to stand trial rating scale in offenders with mental disorders].

PubMed

Chen, Xiao-Bing; Cai, Wei-Xiong

2013-04-01

According with Chinese legal system, to develop a competency to stand trial rating scale in offenders with mental disorders. Proceeding from the juristical elements, 15 items were extracted and formulated a preliminary instrument named the competency to stand trial rating scale in offenders with mental disorders. The item analysis included six aspects, which were critical ratio, item-total correlation, corrected item-total correlation, alpha value if item deleted, communalities of items, and factor loading. The Logistic regression equation and cut-off score of ROC curve were used to explore the diagnostic efficiency. The data of critical ratio of extreme group were 18.390-46.763; item-total correlation, 0.639-0.952; corrected item-total correlation, 0.582-0.944; communalities of items, 0.377-0.916; and factor loadings, 0.614-0.957. Seven items were included in the regression equation and the accuracy of back substitution test was 96.0%. The score of 33 was ascertained as the cut-off score by ROC fitting curve, the overlapping ratio compared with the expertise was 95.8%. The sensibility and the specificity were 0.938 and 0.966, respectively, while the positive and negative likelihood ratios were 27.67 and 0.06, respectively. With all items satisfied the requirement of homogeneity test, the rating scale has a reasonable construct and excellent diagnostic efficiency.

Regression Equations for Estimating Flood Flows at Selected Recurrence Intervals for Ungaged Streams in Pennsylvania

USGS Publications Warehouse

Roland, Mark A.; Stuckey, Marla H.

2008-01-01

Regression equations were developed for estimating flood flows at selected recurrence intervals for ungaged streams in Pennsylvania with drainage areas less than 2,000 square miles. These equations were developed utilizing peak-flow data from 322 streamflow-gaging stations within Pennsylvania and surrounding states. All stations used in the development of the equations had 10 or more years of record and included active and discontinued continuous-record as well as crest-stage partial-record stations. The state was divided into four regions, and regional regression equations were developed to estimate the 2-, 5-, 10-, 50-, 100-, and 500-year recurrence-interval flood flows. The equations were developed by means of a regression analysis that utilized basin characteristics and flow data associated with the stations. Significant explanatory variables at the 95-percent confidence level for one or more regression equations included the following basin characteristics: drainage area; mean basin elevation; and the percentages of carbonate bedrock, urban area, and storage within a basin. The regression equations can be used to predict the magnitude of flood flows for specified recurrence intervals for most streams in the state; however, they are not valid for streams with drainage areas generally greater than 2,000 square miles or with substantial regulation, diversion, or mining activity within the basin. Estimates of flood-flow magnitude and frequency for streamflow-gaging stations substantially affected by upstream regulation are also presented.

Estimating interaction on an additive scale between continuous determinants in a logistic regression model.

PubMed

Knol, Mirjam J; van der Tweel, Ingeborg; Grobbee, Diederick E; Numans, Mattijs E; Geerlings, Mirjam I

2007-10-01

To determine the presence of interaction in epidemiologic research, typically a product term is added to the regression model. In linear regression, the regression coefficient of the product term reflects interaction as departure from additivity. However, in logistic regression it refers to interaction as departure from multiplicativity. Rothman has argued that interaction estimated as departure from additivity better reflects biologic interaction. So far, literature on estimating interaction on an additive scale using logistic regression only focused on dichotomous determinants. The objective of the present study was to provide the methods to estimate interaction between continuous determinants and to illustrate these methods with a clinical example. and results From the existing literature we derived the formulas to quantify interaction as departure from additivity between one continuous and one dichotomous determinant and between two continuous determinants using logistic regression. Bootstrapping was used to calculate the corresponding confidence intervals. To illustrate the theory with an empirical example, data from the Utrecht Health Project were used, with age and body mass index as risk factors for elevated diastolic blood pressure. The methods and formulas presented in this article are intended to assist epidemiologists to calculate interaction on an additive scale between two variables on a certain outcome. The proposed methods are included in a spreadsheet which is freely available at: http://www.juliuscenter.nl/additive-interaction.xls.

Clinical management provided by board-certificated physiatrists in early rehabilitation is a significant determinant of functional improvement in acute stroke patients: a retrospective analysis of Japan rehabilitation database.

PubMed

Kinoshita, Shoji; Kakuda, Wataru; Momosaki, Ryo; Yamada, Naoki; Sugawara, Hidekazu; Watanabe, Shu; Abo, Masahiro

2015-05-01

Early rehabilitation for acute stroke patients is widely recommended. We tested the hypothesis that clinical outcome of stroke patients who receive early rehabilitation managed by board-certificated physiatrists (BCP) is generally better than that provided by other medical specialties. Data of stroke patients who underwent early rehabilitation in 19 acute hospitals between January 2005 and December 2013 were collected from the Japan Rehabilitation Database and analyzed retrospectively. Multivariate linear regression analysis using generalized estimating equations method was performed to assess the association between Functional Independence Measure (FIM) effectiveness and management provided by BCP in early rehabilitation. In addition, multivariate logistic regression analysis was also performed to assess the impact of management provided by BCP in acute phase on discharge destination. After setting the inclusion criteria, data of 3838 stroke patients were eligible for analysis. BCP provided early rehabilitation in 814 patients (21.2%). Both the duration of daily exercise time and the frequency of regular conferencing were significantly higher for patients managed by BCP than by other specialties. Although the mortality rate was not different, multivariate regression analysis showed that FIM effectiveness correlated significantly and positively with the management provided by BCP (coefficient, .35; 95% confidence interval [CI], .012-.059; P < .005). In addition, multivariate logistic analysis identified clinical management by BCP as a significant determinant of home discharge (odds ratio, 1.24; 95% CI, 1.08-1.44; P < .005). Our retrospective cohort study demonstrated that clinical management provided by BCP in early rehabilitation can lead to functional recovery of acute stroke. Copyright © 2015 National Stroke Association. Published by Elsevier Inc. All rights reserved.

Comparing methods of analysing datasets with small clusters: case studies using four paediatric datasets.

PubMed

Marston, Louise; Peacock, Janet L; Yu, Keming; Brocklehurst, Peter; Calvert, Sandra A; Greenough, Anne; Marlow, Neil

2009-07-01

Studies of prematurely born infants contain a relatively large percentage of multiple births, so the resulting data have a hierarchical structure with small clusters of size 1, 2 or 3. Ignoring the clustering may lead to incorrect inferences. The aim of this study was to compare statistical methods which can be used to analyse such data: generalised estimating equations, multilevel models, multiple linear regression and logistic regression. Four datasets which differed in total size and in percentage of multiple births (n = 254, multiple 18%; n = 176, multiple 9%; n = 10 098, multiple 3%; n = 1585, multiple 8%) were analysed. With the continuous outcome, two-level models produced similar results in the larger dataset, while generalised least squares multilevel modelling (ML GLS 'xtreg' in Stata) and maximum likelihood multilevel modelling (ML MLE 'xtmixed' in Stata) produced divergent estimates using the smaller dataset. For the dichotomous outcome, most methods, except generalised least squares multilevel modelling (ML GH 'xtlogit' in Stata) gave similar odds ratios and 95% confidence intervals within datasets. For the continuous outcome, our results suggest using multilevel modelling. We conclude that generalised least squares multilevel modelling (ML GLS 'xtreg' in Stata) and maximum likelihood multilevel modelling (ML MLE 'xtmixed' in Stata) should be used with caution when the dataset is small. Where the outcome is dichotomous and there is a relatively large percentage of non-independent data, it is recommended that these are accounted for in analyses using logistic regression with adjusted standard errors or multilevel modelling. If, however, the dataset has a small percentage of clusters greater than size 1 (e.g. a population dataset of children where there are few multiples) there appears to be less need to adjust for clustering.

Windows of achievement for development milestones of Sri Lankan infants and toddlers: estimation through statistical modelling.

PubMed

Thalagala, N

2015-11-01

The normative age ranges during which cohorts of children achieve milestones are called windows of achievement. The patterns of these windows of achievement are known to be both genetically and environmentally dependent. This study aimed to determine the windows of achievement for motor, social emotional, language and cognitive development milestones for infants and toddlers in Sri Lanka. A set of 293 milestones identified through a literature review were subjected to content validation using parent and expert reviews, which resulted in the selection of a revised set of 277 milestones. Thereafter, a sample of 1036 children from 2 months to 30 months was examined to see whether or not they had attained the selected milestones. Percentile ages of attaining milestone were determined using a rearranged closed form equation related to the logistic regression. The parameters required for calculations were derived through the logistic regression of milestone achievement statuses against ages of children. These percentile ages were used to define the respective windows of achievement. A set of 178 robust indicators that represent motor, socio emotional, language and cognitive development skills and their windows of achievement relevant to 2 to 24 months of age were determined. Windows of achievement for six gross motor milestones determined in the study were shown to closely overlap a similar set of windows of achievement published by the World Health Organization indicating the validity of some findings. A methodology combining the content validation based on qualitative techniques and age validation based on regression modelling found to be effective for determining age percentiles for realizing milestones and determining respective windows of achievement. © 2015 John Wiley & Sons Ltd.

Asymptotic behavior of degenerate logistic equations

NASA Astrophysics Data System (ADS)

Arrieta, José M.; Pardo, Rosa; Rodríguez-Bernal, Aníbal

2015-12-01

We analyze the asymptotic behavior of positive solutions of parabolic equations with a class of degenerate logistic nonlinearities of the type λu - n (x)uρ. An important characteristic of this work is that the region where the logistic term n (ṡ) vanishes, that is K0 = { x : n (x) = 0 }, may be non-smooth. We analyze conditions on λ, ρ, n (ṡ) and K0 guaranteeing that the solution starting at a positive initial condition remains bounded or blows up as time goes to infinity. The asymptotic behavior may not be the same in different parts of K0.

Logits and Tigers and Bears, Oh My! A Brief Look at the Simple Math of Logistic Regression and How It Can Improve Dissemination of Results

ERIC Educational Resources Information Center

Osborne, Jason W.

2012-01-01

Logistic regression is slowly gaining acceptance in the social sciences, and fills an important niche in the researcher's toolkit: being able to predict important outcomes that are not continuous in nature. While OLS regression is a valuable tool, it cannot routinely be used to predict outcomes that are binary or categorical in nature. These…

Religious Coping, Spirituality, and Substance Use and Abuse Among Youth in High-Risk Communities in San Salvador, El Salvador

PubMed Central

Salas-Wright, Christopher P.; Olate, Rene; Vaughn, Michael G.

2014-01-01

Little is known about the relationship between religious coping, spirituality, and substance use in developing nations such as El Salvador. Collected in 2011, the sample consists of 290 high-risk and gang-involved adolescents (11–17 years) and young adults (18–25 years) in San Salvador, El Salvador. Structural equation modeling and logistic regression are employed to examine the associations between the Measure of Religious Coping (RCOPE), the Intrinsic Spirituality Scale, and substance use and abuse. Results suggest that spirituality and, to a far lesser degree, religious coping may serve to protect for substance use and abuse among this high-risk population of Salvadoran youth. PMID:23647129

[The relationship of halitosis and Helicobacter pylori].

PubMed

Chen, Xi; Tao, Dan-ying; Li, Qing; Feng, Xi-ping

2007-06-01

The aim of the study was to investigate the relationship between halitosis and Helicobacter pylori infection in stomach. Fifty subjects without periodontal diseases and systematic disease (exclude gastrointestinal diseases) were included. Infection of H.pylori was diagnosed by biopsy and (14)C-urea breath test. SPSS11.5 software package was used to analyze the data. All the subjects were periodontal healthy according to the periodontal index. The prevalence of H.pylori infection in halitosis subjects was significantly higher than that in the normal subjects (57.1% VS 18.2%, P<0.01). Logistic regression analysis showed that H.pylori was the only significant variable in the equation(P<0.05). H.pylori in stomach may be involved in the presence of halitosis in periodontal healthy subjects.

Recent im/migration to Canada linked to unmet health needs among sex workers in Vancouver, Canada: Findings of a longitudinal study

PubMed Central

Sou, Julie; Goldenberg, Shira M.; Duff, Putu; Nguyen, Paul; Shoveller, Jean; Shannon, Kate

2017-01-01

Despite universal health care in Canada, sex workers (SW) and im/migrants experience suboptimal health care access. In this analysis, we examined the correlates of unmet health needs among SWs in Metro Vancouver over time. Data from a longitudinal cohort of women SWs (AESHA) was used. Of 742 SWs, 25.5% reported unmet health needs at least once over the 4-year study period. In multivariable logistic regression using generalized estimating equations, recent im/migration had the strongest impact on unmet health needs; long-term im/migration, policing, and trauma were also important determinants. Legal and social supports to promote im/migrant SWs’ access to health care are recommended. PMID:28300492

The effects of extraverted temperament on agoraphobia in panic disorder.

PubMed

Rosellini, Anthony J; Lawrence, Amy E; Meyer, Joseph F; Brown, Timothy A

2010-05-01

Although situational avoidance is viewed as the most disabling aspect of panic disorder, few studies have evaluated how dimensions of neurotic (i.e., neuroticism, behavioral inhibition) and extraverted (i.e., extraversion, behavioral activation) temperament may influence the presence and severity of agoraphobia. Using logistic regression and structural equation modeling, we examined the unique effects of extraverted temperament on situational avoidance in a sample of 274 outpatients with a diagnosis of panic disorder with and without agoraphobia. Results showed low extraverted temperament (i.e., introversion) to be associated with both the presence and the severity of situational avoidance. Findings are discussed in regard to conceptualizations of conditioned avoidance, activity levels, sociability, and positive emotions within the context of panic disorder with agoraphobia.

The Effects of Extraverted Temperament on Agoraphobia in Panic Disorder

PubMed Central

Rosellini, Anthony J.; Lawrence, Amy E.; Meyer, Joseph F.; Brown, Timothy A.

2010-01-01

Although situational avoidance is viewed as the most disabling aspect of panic disorder (PD), few studies have evaluated how dimensions of neurotic (i.e., NT; neuroticism, behavioral inhibition) and extraverted (i.e. ET; extraversion, behavioral activation) temperament may influence the presence and severity of agoraphobia (AG). Using logistic regression and structural equation modeling, the present study examined the unique effects of ET on situational avoidance in a sample of 274 outpatients diagnosed with PD with and without AG. Results showed low ET (i.e., introversion) to be associated with both the presence and severity of situational avoidance. Findings are discussed in regard to conceptualizations of conditioned avoidance, activity levels, sociability, and positive emotions within the context of PD with AG. PMID:20455614

Intermediate and advanced topics in multilevel logistic regression analysis

PubMed Central

Merlo, Juan

2017-01-01

Multilevel data occur frequently in health services, population and public health, and epidemiologic research. In such research, binary outcomes are common. Multilevel logistic regression models allow one to account for the clustering of subjects within clusters of higher‐level units when estimating the effect of subject and cluster characteristics on subject outcomes. A search of the PubMed database demonstrated that the use of multilevel or hierarchical regression models is increasing rapidly. However, our impression is that many analysts simply use multilevel regression models to account for the nuisance of within‐cluster homogeneity that is induced by clustering. In this article, we describe a suite of analyses that can complement the fitting of multilevel logistic regression models. These ancillary analyses permit analysts to estimate the marginal or population‐average effect of covariates measured at the subject and cluster level, in contrast to the within‐cluster or cluster‐specific effects arising from the original multilevel logistic regression model. We describe the interval odds ratio and the proportion of opposed odds ratios, which are summary measures of effect for cluster‐level covariates. We describe the variance partition coefficient and the median odds ratio which are measures of components of variance and heterogeneity in outcomes. These measures allow one to quantify the magnitude of the general contextual effect. We describe an R 2 measure that allows analysts to quantify the proportion of variation explained by different multilevel logistic regression models. We illustrate the application and interpretation of these measures by analyzing mortality in patients hospitalized with a diagnosis of acute myocardial infarction. © 2017 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd. PMID:28543517

Intermediate and advanced topics in multilevel logistic regression analysis.

PubMed

Austin, Peter C; Merlo, Juan

2017-09-10

Multilevel data occur frequently in health services, population and public health, and epidemiologic research. In such research, binary outcomes are common. Multilevel logistic regression models allow one to account for the clustering of subjects within clusters of higher-level units when estimating the effect of subject and cluster characteristics on subject outcomes. A search of the PubMed database demonstrated that the use of multilevel or hierarchical regression models is increasing rapidly. However, our impression is that many analysts simply use multilevel regression models to account for the nuisance of within-cluster homogeneity that is induced by clustering. In this article, we describe a suite of analyses that can complement the fitting of multilevel logistic regression models. These ancillary analyses permit analysts to estimate the marginal or population-average effect of covariates measured at the subject and cluster level, in contrast to the within-cluster or cluster-specific effects arising from the original multilevel logistic regression model. We describe the interval odds ratio and the proportion of opposed odds ratios, which are summary measures of effect for cluster-level covariates. We describe the variance partition coefficient and the median odds ratio which are measures of components of variance and heterogeneity in outcomes. These measures allow one to quantify the magnitude of the general contextual effect. We describe an R 2 measure that allows analysts to quantify the proportion of variation explained by different multilevel logistic regression models. We illustrate the application and interpretation of these measures by analyzing mortality in patients hospitalized with a diagnosis of acute myocardial infarction. © 2017 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd. © 2017 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.

Automated particle identification through regression analysis of size, shape and colour

NASA Astrophysics Data System (ADS)

Rodriguez Luna, J. C.; Cooper, J. M.; Neale, S. L.

2016-04-01

Rapid point of care diagnostic tests and tests to provide therapeutic information are now available for a range of specific conditions from the measurement of blood glucose levels for diabetes to card agglutination tests for parasitic infections. Due to a lack of specificity these test are often then backed up by more conventional lab based diagnostic methods for example a card agglutination test may be carried out for a suspected parasitic infection in the field and if positive a blood sample can then be sent to a lab for confirmation. The eventual diagnosis is often achieved by microscopic examination of the sample. In this paper we propose a computerized vision system for aiding in the diagnostic process; this system used a novel particle recognition algorithm to improve specificity and speed during the diagnostic process. We will show the detection and classification of different types of cells in a diluted blood sample using regression analysis of their size, shape and colour. The first step is to define the objects to be tracked by a Gaussian Mixture Model for background subtraction and binary opening and closing for noise suppression. After subtracting the objects of interest from the background the next challenge is to predict if a given object belongs to a certain category or not. This is a classification problem, and the output of the algorithm is a Boolean value (true/false). As such the computer program should be able to "predict" with reasonable level of confidence if a given particle belongs to the kind we are looking for or not. We show the use of a binary logistic regression analysis with three continuous predictors: size, shape and color histogram. The results suggest this variables could be very useful in a logistic regression equation as they proved to have a relatively high predictive value on their own.

Uniqueness of boundary blow-up solutions on exterior domain of RN

NASA Astrophysics Data System (ADS)

Dong, Wei; Pang, Changci

2007-06-01

In this paper, we consider the existence and uniqueness of positive solutions of the degenerate logistic type elliptic equation where N[greater-or-equal, slanted]2, D[subset of]RN is a bounded domain with smooth boundary and a(x), b(x) are continuous functions on RN with b(x)[greater-or-equal, slanted]0, b(x)[not identical with]0. We show that under rather general conditions on a(x) and b(x) for large x, there exists a unique positive solution. Our results improve the corresponding ones in [W. Dong, Y. Du, Unbounded principal eigenfunctions and the logistic equation on RN, Bull. Austral. Math. Soc. 67 (2003) 413-427] and [Y. Du, L. Ma, Logistic type equations on RN by a squeezing method involving boundary blow-up solutions, J. London Math. Soc. (2) 64 (2001) 107-124].

Regression equations to estimate seasonal flow duration, n-day high-flow frequency, and n-day low-flow frequency at sites in North Dakota using data through water year 2009

USGS Publications Warehouse

Williams-Sether, Tara; Gross, Tara A.

2016-02-09

Seasonal mean daily flow data from 119 U.S. Geological Survey streamflow-gaging stations in North Dakota; the surrounding states of Montana, Minnesota, and South Dakota; and the Canadian provinces of Manitoba and Saskatchewan with 10 or more years of unregulated flow record were used to develop regression equations for flow duration, n-day high flow and n-day low flow using ordinary least-squares and Tobit regression techniques. Regression equations were developed for seasonal flow durations at the 10th, 25th, 50th, 75th, and 90th percent exceedances; the 1-, 7-, and 30-day seasonal mean high flows for the 10-, 25-, and 50-year recurrence intervals; and the 1-, 7-, and 30-day seasonal mean low flows for the 2-, 5-, and 10-year recurrence intervals. Basin and climatic characteristics determined to be significant explanatory variables in one or more regression equations included drainage area, percentage of basin drainage area that drains to isolated lakes and ponds, ruggedness number, stream length, basin compactness ratio, minimum basin elevation, precipitation, slope ratio, stream slope, and soil permeability. The adjusted coefficient of determination for the n-day high-flow regression equations ranged from 55.87 to 94.53 percent. The Chi2 values for the duration regression equations ranged from 13.49 to 117.94, whereas the Chi2 values for the n-day low-flow regression equations ranged from 4.20 to 49.68.

Predicting Social Trust with Binary Logistic Regression

ERIC Educational Resources Information Center

Adwere-Boamah, Joseph; Hufstedler, Shirley

2015-01-01

This study used binary logistic regression to predict social trust with five demographic variables from a national sample of adult individuals who participated in The General Social Survey (GSS) in 2012. The five predictor variables were respondents' highest degree earned, race, sex, general happiness and the importance of personally assisting…

Effect of folic acid on appetite in children: ordinal logistic and fuzzy logistic regressions.

PubMed

Namdari, Mahshid; Abadi, Alireza; Taheri, S Mahmoud; Rezaei, Mansour; Kalantari, Naser; Omidvar, Nasrin

2014-03-01

Reduced appetite and low food intake are often a concern in preschool children, since it can lead to malnutrition, a leading cause of impaired growth and mortality in childhood. It is occasionally considered that folic acid has a positive effect on appetite enhancement and consequently growth in children. The aim of this study was to assess the effect of folic acid on the appetite of preschool children 3 to 6 y old. The study sample included 127 children ages 3 to 6 who were randomly selected from 20 preschools in the city of Tehran in 2011. Since appetite was measured by linguistic terms, a fuzzy logistic regression was applied for modeling. The obtained results were compared with a statistical ordinal logistic model. After controlling for the potential confounders, in a statistical ordinal logistic model, serum folate showed a significantly positive effect on appetite. A small but positive effect of folate was detected by fuzzy logistic regression. Based on fuzzy regression, the risk for poor appetite in preschool children was related to the employment status of their mothers. In this study, a positive association was detected between the levels of serum folate and improved appetite. For further investigation, a randomized controlled, double-blind clinical trial could be helpful to address causality. Copyright © 2014 Elsevier Inc. All rights reserved.

The Effect of Repeaters on Equating

ERIC Educational Resources Information Center

Kim, HeeKyoung; Kolen, Michael J.

2010-01-01

Test equating might be affected by including in the equating analyses examinees who have taken the test previously. This study evaluated the effect of including such repeaters on Medical College Admission Test (MCAT) equating using a population invariance approach. Three-parameter logistic (3-PL) item response theory (IRT) true score and…

Factors influencing hospital high length of stay outliers

PubMed Central

2012-01-01

Background The study of length of stay (LOS) outliers is important for the management and financing of hospitals. Our aim was to study variables associated with high LOS outliers and their evolution over time. Methods We used hospital administrative data from inpatient episodes in public acute care hospitals in the Portuguese National Health Service (NHS), with discharges between years 2000 and 2009, together with some hospital characteristics. The dependent variable, LOS outliers, was calculated for each diagnosis related group (DRG) using a trim point defined for each year by the geometric mean plus two standard deviations. Hospitals were classified on the basis of administrative, economic and teaching characteristics. We also studied the influence of comorbidities and readmissions. Logistic regression models, including a multivariable logistic regression, were used in the analysis. All the logistic regressions were fitted using generalized estimating equations (GEE). Results In near nine million inpatient episodes analysed we found a proportion of 3.9% high LOS outliers, accounting for 19.2% of total inpatient days. The number of hospital patient discharges increased between years 2000 and 2005 and slightly decreased after that. The proportion of outliers ranged between the lowest value of 3.6% (in years 2001 and 2002) and the highest value of 4.3% in 2009. Teaching hospitals with over 1,000 beds have significantly more outliers than other hospitals, even after adjustment to readmissions and several patient characteristics. Conclusions In the last years both average LOS and high LOS outliers are increasing in Portuguese NHS hospitals. As high LOS outliers represent an important proportion in the total inpatient days, this should be seen as an important alert for the management of hospitals and for national health policies. As expected, age, type of admission, and hospital type were significantly associated with high LOS outliers. The proportion of high outliers does not seem to be related to their financial coverage; they should be studied in order to highlight areas for further investigation. The increasing complexity of both hospitals and patients may be the single most important determinant of high LOS outliers and must therefore be taken into account by health managers when considering hospital costs. PMID:22906386

Comparing the IRT Pre-equating and Section Pre-equating: A Simulation Study.

ERIC Educational Resources Information Center

Hwang, Chi-en; Cleary, T. Anne

The results obtained from two basic types of pre-equatings of tests were compared: the item response theory (IRT) pre-equating and section pre-equating (SPE). The simulated data were generated from a modified three-parameter logistic model with a constant guessing parameter. Responses of two replication samples of 3000 examinees on two 72-item…

Clustering performance comparison using K-means and expectation maximization algorithms.

PubMed

Jung, Yong Gyu; Kang, Min Soo; Heo, Jun

2014-11-14

Clustering is an important means of data mining based on separating data categories by similar features. Unlike the classification algorithm, clustering belongs to the unsupervised type of algorithms. Two representatives of the clustering algorithms are the K -means and the expectation maximization (EM) algorithm. Linear regression analysis was extended to the category-type dependent variable, while logistic regression was achieved using a linear combination of independent variables. To predict the possibility of occurrence of an event, a statistical approach is used. However, the classification of all data by means of logistic regression analysis cannot guarantee the accuracy of the results. In this paper, the logistic regression analysis is applied to EM clusters and the K -means clustering method for quality assessment of red wine, and a method is proposed for ensuring the accuracy of the classification results.

Racial/ethnic and educational differences in the estimated odds of recent nitrite use among adult household residents in the United States: an illustration of matching and conditional logistic regression.

PubMed

Delva, J; Spencer, M S; Lin, J K

2000-01-01

This article compares estimates of the relative odds of nitrite use obtained from weighted unconditional logistic regression with estimates obtained from conditional logistic regression after post-stratification and matching of cases with controls by neighborhood of residence. We illustrate these methods by comparing the odds associated with nitrite use among adults of four racial/ethnic groups, with and without a high school education. We used aggregated data from the 1994-B through 1996 National Household Survey on Drug Abuse (NHSDA). Difference between the methods and implications for analysis and inference are discussed.

Regression trees for predicting mortality in patients with cardiovascular disease: What improvement is achieved by using ensemble-based methods?

PubMed Central

Austin, Peter C; Lee, Douglas S; Steyerberg, Ewout W; Tu, Jack V

2012-01-01

In biomedical research, the logistic regression model is the most commonly used method for predicting the probability of a binary outcome. While many clinical researchers have expressed an enthusiasm for regression trees, this method may have limited accuracy for predicting health outcomes. We aimed to evaluate the improvement that is achieved by using ensemble-based methods, including bootstrap aggregation (bagging) of regression trees, random forests, and boosted regression trees. We analyzed 30-day mortality in two large cohorts of patients hospitalized with either acute myocardial infarction (N = 16,230) or congestive heart failure (N = 15,848) in two distinct eras (1999–2001 and 2004–2005). We found that both the in-sample and out-of-sample prediction of ensemble methods offered substantial improvement in predicting cardiovascular mortality compared to conventional regression trees. However, conventional logistic regression models that incorporated restricted cubic smoothing splines had even better performance. We conclude that ensemble methods from the data mining and machine learning literature increase the predictive performance of regression trees, but may not lead to clear advantages over conventional logistic regression models for predicting short-term mortality in population-based samples of subjects with cardiovascular disease. PMID:22777999

[Ultrasonic measurements of fetal thalamus, caudate nucleus and lenticular nucleus in prenatal diagnosis].

PubMed

Yang, Ruiqi; Wang, Fei; Zhang, Jialing; Zhu, Chonglei; Fan, Limei

2015-05-19

To establish the reference values of thalamus, caudate nucleus and lenticular nucleus diameters through fetal thalamic transverse section. A total of 265 fetuses at our hospital were randomly selected from November 2012 to August 2014. And the transverse and length diameters of thalamus, caudate nucleus and lenticular nucleus were measured. SPSS 19.0 statistical software was used to calculate the regression curve of fetal diameter changes and gestational weeks of pregnancy. P < 0.05 was considered as having statistical significance. The linear regression equation of fetal thalamic length diameter and gestational week was: Y = 0.051X+0.201, R = 0.876, linear regression equation of thalamic transverse diameter and fetal gestational week was: Y = 0.031X+0.229, R = 0.817, linear regression equation of fetal head of caudate nucleus length diameter and gestational age was: Y = 0.033X+0.101, R = 0.722, linear regression equation of fetal head of caudate nucleus transverse diameter and gestational week was: R = 0.025 - 0.046, R = 0.711, linear regression equation of fetal lentiform nucleus length diameter and gestational week was: Y = 0.046+0.229, R = 0.765, linear regression equation of fetal lentiform nucleus diameter and gestational week was: Y = 0.025 - 0.05, R = 0.772. Ultrasonic measurement of diameter of fetal thalamus caudate nucleus, and lenticular nucleus through thalamic transverse section is simple and convenient. And measurements increase with fetal gestational weeks and there is linear regression relationship between them.

Effects of edaravone on early outcomes in acute ischemic stroke patients treated with recombinant tissue plasminogen activator.

PubMed

Wada, Tomoki; Yasunaga, Hideo; Inokuchi, Ryota; Horiguchi, Hiromasa; Fushimi, Kiyohide; Matsubara, Takehiro; Nakajima, Susumu; Yahagi, Naoki

2014-10-15

We investigated whether edaravone could improve early outcomes in acute ischemic stroke patients treated with recombinant tissue plasminogen activator (rtPA). We conducted a retrospective cohort study using the Japanese Diagnosis Procedure Combination database. We identified patients admitted with a primary diagnosis of ischemic stroke from 1 July 2010 to 31 March 2012 and treated with rtPA on the same day of stroke onset or the following day. Thereafter, we selected those who received edaravone on the same day of rtPA administration (edaravone group), and those who received rtPA without edaravone (control group). The primary outcomes were modified Rankin Scale (mRS) scores at discharge. One-to-one propensity-score matching was performed between the edaravone and control groups. An ordinal logistic regression analysis for mRS scores at discharge was performed with adjustment for possible variables as well as clustering of patients within hospitals using a generalized estimating equation. We identified 6336 eligible patients for inclusion in the edaravone group (n=5979; 94%) and the control group (n=357; 6%) as the total population. In 356 pairs of the propensity-matched population, the ordinal logistic regression analysis showed that edaravone was significantly associated with lower mRS scores of patients at discharge (adjusted odds ratio: 0.74; 95% confidence interval: 0.57-0.96). Edaravone may improve early outcomes in acute ischemic stroke patients treated with rtPA. Copyright © 2014 Elsevier B.V. All rights reserved.

Family-centered prevention ameliorates the association between adverse childhood experiences and prediabetes status in young black adults.

PubMed

Brody, Gene H; Yu, Tianyi; Chen, Edith; Miller, Gregory E

2017-07-01

Individuals exposed to adverse childhood experiences (ACEs) are vulnerable to various health problems later in life. This study was designed to determine whether participation in an efficacious program to enhance supportive parenting would ameliorate the association between ACEs and prediabetes status at age 25. Rural African American parents and their 11-year-old children (N=390) participated in the Strong African American Families (SAAF) program or a control condition. Each youth at age 25 provided a total ACEs score and a blood sample from which overnight fasting glucose was assayed. Logistic regression equations were used to test the hypotheses. The logistic regression analyses revealed a significant interaction between total ACEs and random assignment to SAAF or control, OR=0.56, 95% CI [0.36, 0.88]. Follow-up analyses indicated that, for participants in the control condition, a 1-point increase in ACEs was associated with a 37.3% increase in risk of having prediabetes. ACEs were not associated with the likelihood of having prediabetes among participants in the SAAF condition. Control participants with high total ACEs scores were 3.54 times more likely to have prediabetes than were SAAF participants with similar scores. This study indicated that participation at age 11 in a randomized controlled trial designed to enhance supportive parenting ameliorated the association of ACEs with prediabetes at age 25. If substantiated, these findings may provide a strategy for preventing negative health consequences of ACEs. Copyright © 2017 Elsevier Inc. All rights reserved.

Resilience model for parents of children with cancer in mainland China-An exploratory study.

PubMed

Ye, Zeng Jie; Qiu, Hong Zhong; Li, Peng Fei; Liang, Mu Zi; Wang, Shu Ni; Quan, Xiao Ming

2017-04-01

Parents have psychosocial functions that are critical for the entire family. Therefore, when their child is diagnosed with cancer, it is important that they exhibit resilience, which is the ability to preserve their emotional and physical well-being in the face of stress. The Resilience Model for Parents of Children with Cancer (RMP-CC) was developed to increase our understanding of how resilience is positively and negatively affected by protective and risk factors, respectively, in Chinese parents with children diagnosed with cancer. To evaluate the RMP-CC, the latent psychosocial variables and demographics of 229 parents were evaluated using exploratory structural equation modeling (SEM) and logistic regression. The majority of goodness-of-fit indices indicate that the SEM of RMP-CC was a good model with a high level of variance in resilience (58%). Logistic regression revealed that two demographics, educational level and clinical classification of cancer, accounted for 12% of this variance. Our results indicate that RMP-CC is an effective structure by which to develop mainland Chinese parent-focused interventions that are grounded in the experiences of the parents as caregivers of children who have been diagnosed with cancer. RMP-CC allows for a better understanding of what these parents experience while their children undergo treatment. Further studies will be needed to confirm the efficiency of the current structure, and would assist in further refinement of its clinical applications. Copyright © 2017 Elsevier Ltd. All rights reserved.

Healthcare Utilization and Expenditures for Persons with Diabetes Comorbid with Mental Illnesses.

PubMed

Su, Chen-Hsiang; Chiu, Herng-Chia; Hsieh, Hui-Min; Yen, Ju-Yu; Lee, Mei-Hsuan; Li, Chih-Yi; Chang, Kao-Ping; Huang, Chun-Jen

2016-09-01

The aim of this study was to investigate healthcare utilization and expenditure for patients with diabetes comorbid with and without mental illnesses in Taiwan. People with diabetes comorbid with and without mental illnesses in 2000 were identified and followed up to 2004 to explore the healthcare utilization and expenditure. Healthcare utilization included outpatient visits and use of hospital inpatient services, and expenditure included outpatient, inpatient and total medical expenditure. General estimation equation models were used to explore the factors associated with outpatient visits and expenditure. To identify the factors associated with hospitalization, multiple logistic regressions were applied. The average number of annual outpatient visits of the patients with mental illnesses ranged from 37.01 to 41.91, and 28.83 to 31.79 times for the patients without mental illnesses from 2000 to 2004. The average annual total expenditure for patients with mental illnesses during this period ranged from NT$77,123-NT$90,790, and NT$60,793- NT$84,984 for those without mental illnesses. After controlling for covariates, the results indicated that gender, age, mental illness and time factor were associated with outpatient visits. Gender, age, and time factor were associated with total expenditure. Age and mental illness were associated with hospitalization in logistic regression. The healthcare utilization and expenditure for patients with mental illnesses was significantly higher than for patients without mental illnesses. The factors associated with healthcare utilization and expenditure included gender, age, mental illness and time trends.

A Comparison of Kernel Equating and Traditional Equipercentile Equating Methods and the Parametric Bootstrap Methods for Estimating Standard Errors in Equipercentile Equating

ERIC Educational Resources Information Center

Choi, Sae Il

2009-01-01

This study used simulation (a) to compare the kernel equating method to traditional equipercentile equating methods under the equivalent-groups (EG) design and the nonequivalent-groups with anchor test (NEAT) design and (b) to apply the parametric bootstrap method for estimating standard errors of equating. A two-parameter logistic item response…

Strategies for Testing Statistical and Practical Significance in Detecting DIF with Logistic Regression Models

ERIC Educational Resources Information Center

Fidalgo, Angel M.; Alavi, Seyed Mohammad; Amirian, Seyed Mohammad Reza

2014-01-01

This study examines three controversial aspects in differential item functioning (DIF) detection by logistic regression (LR) models: first, the relative effectiveness of different analytical strategies for detecting DIF; second, the suitability of the Wald statistic for determining the statistical significance of the parameters of interest; and…

Iterative Purification and Effect Size Use with Logistic Regression for Differential Item Functioning Detection

ERIC Educational Resources Information Center

French, Brian F.; Maller, Susan J.

2007-01-01

Two unresolved implementation issues with logistic regression (LR) for differential item functioning (DIF) detection include ability purification and effect size use. Purification is suggested to control inaccuracies in DIF detection as a result of DIF items in the ability estimate. Additionally, effect size use may be beneficial in controlling…

A Note on Three Statistical Tests in the Logistic Regression DIF Procedure

ERIC Educational Resources Information Center

Paek, Insu

2012-01-01

Although logistic regression became one of the well-known methods in detecting differential item functioning (DIF), its three statistical tests, the Wald, likelihood ratio (LR), and score tests, which are readily available under the maximum likelihood, do not seem to be consistently distinguished in DIF literature. This paper provides a clarifying…

"Let Me Count the Ways:" Fostering Reasons for Living among Low-Income, Suicidal, African American Women

ERIC Educational Resources Information Center

West, Lindsey M.; Davis, Telsie A.; Thompson, Martie P.; Kaslow, Nadine J.

2011-01-01

Protective factors for fostering reasons for living were examined among low-income, suicidal, African American women. Bivariate logistic regressions revealed that higher levels of optimism, spiritual well-being, and family social support predicted reasons for living. Multivariate logistic regressions indicated that spiritual well-being showed…

Comparison of Two Approaches for Handling Missing Covariates in Logistic Regression

ERIC Educational Resources Information Center

Peng, Chao-Ying Joanne; Zhu, Jin

2008-01-01

For the past 25 years, methodological advances have been made in missing data treatment. Most published work has focused on missing data in dependent variables under various conditions. The present study seeks to fill the void by comparing two approaches for handling missing data in categorical covariates in logistic regression: the…

Comparison of IRT Likelihood Ratio Test and Logistic Regression DIF Detection Procedures

ERIC Educational Resources Information Center

Atar, Burcu; Kamata, Akihito

2011-01-01

The Type I error rates and the power of IRT likelihood ratio test and cumulative logit ordinal logistic regression procedures in detecting differential item functioning (DIF) for polytomously scored items were investigated in this Monte Carlo simulation study. For this purpose, 54 simulation conditions (combinations of 3 sample sizes, 2 sample…

Multiple Logistic Regression Analysis of Cigarette Use among High School Students

ERIC Educational Resources Information Center

Adwere-Boamah, Joseph

2011-01-01

A binary logistic regression analysis was performed to predict high school students' cigarette smoking behavior from selected predictors from 2009 CDC Youth Risk Behavior Surveillance Survey. The specific target student behavior of interest was frequent cigarette use. Five predictor variables included in the model were: a) race, b) frequency of…

Modeling Polytomous Item Responses Using Simultaneously Estimated Multinomial Logistic Regression Models

ERIC Educational Resources Information Center

Anderson, Carolyn J.; Verkuilen, Jay; Peyton, Buddy L.

2010-01-01

Survey items with multiple response categories and multiple-choice test questions are ubiquitous in psychological and educational research. We illustrate the use of log-multiplicative association (LMA) models that are extensions of the well-known multinomial logistic regression model for multiple dependent outcome variables to reanalyze a set of…

Propensity Score Estimation with Data Mining Techniques: Alternatives to Logistic Regression

ERIC Educational Resources Information Center

Keller, Bryan S. B.; Kim, Jee-Seon; Steiner, Peter M.

2013-01-01

Propensity score analysis (PSA) is a methodological technique which may correct for selection bias in a quasi-experiment by modeling the selection process using observed covariates. Because logistic regression is well understood by researchers in a variety of fields and easy to implement in a number of popular software packages, it has…

Two-factor logistic regression in pediatric liver transplantation

NASA Astrophysics Data System (ADS)

Uzunova, Yordanka; Prodanova, Krasimira; Spasov, Lyubomir

2017-12-01

Using a two-factor logistic regression analysis an estimate is derived for the probability of absence of infections in the early postoperative period after pediatric liver transplantation. The influence of both the bilirubin level and the international normalized ratio of prothrombin time of blood coagulation at the 5th postoperative day is studied.

Predictors of Placement Stability at the State Level: The Use of Logistic Regression to Inform Practice

ERIC Educational Resources Information Center

Courtney, Jon R.; Prophet, Retta

2011-01-01

Placement instability is often associated with a number of negative outcomes for children. To gain state level contextual knowledge of factors associated with placement stability/instability, logistic regression was applied to selected variables from the New Mexico Adoption and Foster Care Administrative Reporting System dataset. Predictors…

Classifying machinery condition using oil samples and binary logistic regression

NASA Astrophysics Data System (ADS)

Phillips, J.; Cripps, E.; Lau, John W.; Hodkiewicz, M. R.

2015-08-01

The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically "black box" approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.

Length bias correction in gene ontology enrichment analysis using logistic regression.

PubMed

Mi, Gu; Di, Yanming; Emerson, Sarah; Cumbie, Jason S; Chang, Jeff H

2012-01-01

When assessing differential gene expression from RNA sequencing data, commonly used statistical tests tend to have greater power to detect differential expression of genes encoding longer transcripts. This phenomenon, called "length bias", will influence subsequent analyses such as Gene Ontology enrichment analysis. In the presence of length bias, Gene Ontology categories that include longer genes are more likely to be identified as enriched. These categories, however, are not necessarily biologically more relevant. We show that one can effectively adjust for length bias in Gene Ontology analysis by including transcript length as a covariate in a logistic regression model. The logistic regression model makes the statistical issue underlying length bias more transparent: transcript length becomes a confounding factor when it correlates with both the Gene Ontology membership and the significance of the differential expression test. The inclusion of the transcript length as a covariate allows one to investigate the direct correlation between the Gene Ontology membership and the significance of testing differential expression, conditional on the transcript length. We present both real and simulated data examples to show that the logistic regression approach is simple, effective, and flexible.

Matched samples logistic regression in case-control studies with missing values: when to break the matches.

PubMed

Hansson, Lisbeth; Khamis, Harry J

2008-12-01

Simulated data sets are used to evaluate conditional and unconditional maximum likelihood estimation in an individual case-control design with continuous covariates when there are different rates of excluded cases and different levels of other design parameters. The effectiveness of the estimation procedures is measured by method bias, variance of the estimators, root mean square error (RMSE) for logistic regression and the percentage of explained variation. Conditional estimation leads to higher RMSE than unconditional estimation in the presence of missing observations, especially for 1:1 matching. The RMSE is higher for the smaller stratum size, especially for the 1:1 matching. The percentage of explained variation appears to be insensitive to missing data, but is generally higher for the conditional estimation than for the unconditional estimation. It is particularly good for the 1:2 matching design. For minimizing RMSE, a high matching ratio is recommended; in this case, conditional and unconditional logistic regression models yield comparable levels of effectiveness. For maximizing the percentage of explained variation, the 1:2 matching design with the conditional logistic regression model is recommended.

Label-noise resistant logistic regression for functional data classification with an application to Alzheimer's disease study.

PubMed

Lee, Seokho; Shin, Hyejin; Lee, Sang Han

2016-12-01

Alzheimer's disease (AD) is usually diagnosed by clinicians through cognitive and functional performance test with a potential risk of misdiagnosis. Since the progression of AD is known to cause structural changes in the corpus callosum (CC), the CC thickness can be used as a functional covariate in AD classification problem for a diagnosis. However, misclassified class labels negatively impact the classification performance. Motivated by AD-CC association studies, we propose a logistic regression for functional data classification that is robust to misdiagnosis or label noise. Specifically, our logistic regression model is constructed by adopting individual intercepts to functional logistic regression model. This approach enables to indicate which observations are possibly mislabeled and also lead to a robust and efficient classifier. An effective algorithm using MM algorithm provides simple closed-form update formulas. We test our method using synthetic datasets to demonstrate its superiority over an existing method, and apply it to differentiating patients with AD from healthy normals based on CC from MRI. © 2016, The International Biometric Society.

The Effect of Latent Binary Variables on the Uncertainty of the Prediction of a Dichotomous Outcome Using Logistic Regression Based Propensity Score Matching.

PubMed

Szekér, Szabolcs; Vathy-Fogarassy, Ágnes

2018-01-01

Logistic regression based propensity score matching is a widely used method in case-control studies to select the individuals of the control group. This method creates a suitable control group if all factors affecting the output variable are known. However, if relevant latent variables exist as well, which are not taken into account during the calculations, the quality of the control group is uncertain. In this paper, we present a statistics-based research in which we try to determine the relationship between the accuracy of the logistic regression model and the uncertainty of the dependent variable of the control group defined by propensity score matching. Our analyses show that there is a linear correlation between the fit of the logistic regression model and the uncertainty of the output variable. In certain cases, a latent binary explanatory variable can result in a relative error of up to 70% in the prediction of the outcome variable. The observed phenomenon calls the attention of analysts to an important point, which must be taken into account when deducting conclusions.

Estimating design-flood discharges for streams in Iowa using drainage-basin and channel-geometry characteristics

USGS Publications Warehouse

Eash, D.A.

1993-01-01

Procedures provided for applying the drainage-basin and channel-geometry regression equations depend on whether the design-flood discharge estimate is for a site on an ungaged stream, an ungaged site on a gaged stream, or a gaged site. When both a drainage-basin and a channel-geometry regression-equation estimate are available for a stream site, a procedure is presented for determining a weighted average of the two flood estimates. The drainage-basin regression equations are applicable to unregulated rural drainage areas less than 1,060 square miles, and the channel-geometry regression equations are applicable to unregulated rural streams in Iowa with stabilized channels.

Logistic regression for circular data

NASA Astrophysics Data System (ADS)

Al-Daffaie, Kadhem; Khan, Shahjahan

2017-05-01

This paper considers the relationship between a binary response and a circular predictor. It develops the logistic regression model by employing the linear-circular regression approach. The maximum likelihood method is used to estimate the parameters. The Newton-Raphson numerical method is used to find the estimated values of the parameters. A data set from weather records of Toowoomba city is analysed by the proposed methods. Moreover, a simulation study is considered. The R software is used for all computations and simulations.

Naval Research Logistics Quarterly. Volume 28. Number 3,

DTIC Science & Technology

1981-09-01

denotes component-wise maximum. f has antone (isotone) differences on C x D if for cl < c2 and d, < d2, NAVAL RESEARCH LOGISTICS QUARTERLY VOL. 28...or negative correlations and linear or nonlinear regressions. Given are the mo- ments to order two and, for special cases, (he regression function and...data sets. We designate this bnb distribution as G - B - N(a, 0, v). The distribution admits only of positive correlation and linear regressions

Regression approaches in the test-negative study design for assessment of influenza vaccine effectiveness.

PubMed

Bond, H S; Sullivan, S G; Cowling, B J

2016-06-01

Influenza vaccination is the most practical means available for preventing influenza virus infection and is widely used in many countries. Because vaccine components and circulating strains frequently change, it is important to continually monitor vaccine effectiveness (VE). The test-negative design is frequently used to estimate VE. In this design, patients meeting the same clinical case definition are recruited and tested for influenza; those who test positive are the cases and those who test negative form the comparison group. When determining VE in these studies, the typical approach has been to use logistic regression, adjusting for potential confounders. Because vaccine coverage and influenza incidence change throughout the season, time is included among these confounders. While most studies use unconditional logistic regression, adjusting for time, an alternative approach is to use conditional logistic regression, matching on time. Here, we used simulation data to examine the potential for both regression approaches to permit accurate and robust estimates of VE. In situations where vaccine coverage changed during the influenza season, the conditional model and unconditional models adjusting for categorical week and using a spline function for week provided more accurate estimates. We illustrated the two approaches on data from a test-negative study of influenza VE against hospitalization in children in Hong Kong which resulted in the conditional logistic regression model providing the best fit to the data.

A novel hybrid method of beta-turn identification in protein using binary logistic regression and neural network

PubMed Central

Asghari, Mehdi Poursheikhali; Hayatshahi, Sayyed Hamed Sadat; Abdolmaleki, Parviz

2012-01-01

From both the structural and functional points of view, β-turns play important biological roles in proteins. In the present study, a novel two-stage hybrid procedure has been developed to identify β-turns in proteins. Binary logistic regression was initially used for the first time to select significant sequence parameters in identification of β-turns due to a re-substitution test procedure. Sequence parameters were consisted of 80 amino acid positional occurrences and 20 amino acid percentages in sequence. Among these parameters, the most significant ones which were selected by binary logistic regression model, were percentages of Gly, Ser and the occurrence of Asn in position i+2, respectively, in sequence. These significant parameters have the highest effect on the constitution of a β-turn sequence. A neural network model was then constructed and fed by the parameters selected by binary logistic regression to build a hybrid predictor. The networks have been trained and tested on a non-homologous dataset of 565 protein chains. With applying a nine fold cross-validation test on the dataset, the network reached an overall accuracy (Qtotal) of 74, which is comparable with results of the other β-turn prediction methods. In conclusion, this study proves that the parameter selection ability of binary logistic regression together with the prediction capability of neural networks lead to the development of more precise models for identifying β-turns in proteins. PMID:27418910

A novel hybrid method of beta-turn identification in protein using binary logistic regression and neural network.

PubMed

Asghari, Mehdi Poursheikhali; Hayatshahi, Sayyed Hamed Sadat; Abdolmaleki, Parviz

2012-01-01

From both the structural and functional points of view, β-turns play important biological roles in proteins. In the present study, a novel two-stage hybrid procedure has been developed to identify β-turns in proteins. Binary logistic regression was initially used for the first time to select significant sequence parameters in identification of β-turns due to a re-substitution test procedure. Sequence parameters were consisted of 80 amino acid positional occurrences and 20 amino acid percentages in sequence. Among these parameters, the most significant ones which were selected by binary logistic regression model, were percentages of Gly, Ser and the occurrence of Asn in position i+2, respectively, in sequence. These significant parameters have the highest effect on the constitution of a β-turn sequence. A neural network model was then constructed and fed by the parameters selected by binary logistic regression to build a hybrid predictor. The networks have been trained and tested on a non-homologous dataset of 565 protein chains. With applying a nine fold cross-validation test on the dataset, the network reached an overall accuracy (Qtotal) of 74, which is comparable with results of the other β-turn prediction methods. In conclusion, this study proves that the parameter selection ability of binary logistic regression together with the prediction capability of neural networks lead to the development of more precise models for identifying β-turns in proteins.

Differential item functioning analysis with ordinal logistic regression techniques. DIFdetect and difwithpar.

PubMed

Crane, Paul K; Gibbons, Laura E; Jolley, Lance; van Belle, Gerald

2006-11-01

We present an ordinal logistic regression model for identification of items with differential item functioning (DIF) and apply this model to a Mini-Mental State Examination (MMSE) dataset. We employ item response theory ability estimation in our models. Three nested ordinal logistic regression models are applied to each item. Model testing begins with examination of the statistical significance of the interaction term between ability and the group indicator, consistent with nonuniform DIF. Then we turn our attention to the coefficient of the ability term in models with and without the group term. If including the group term has a marked effect on that coefficient, we declare that it has uniform DIF. We examined DIF related to language of test administration in addition to self-reported race, Hispanic ethnicity, age, years of education, and sex. We used PARSCALE for IRT analyses and STATA for ordinal logistic regression approaches. We used an iterative technique for adjusting IRT ability estimates on the basis of DIF findings. Five items were found to have DIF related to language. These same items also had DIF related to other covariates. The ordinal logistic regression approach to DIF detection, when combined with IRT ability estimates, provides a reasonable alternative for DIF detection. There appear to be several items with significant DIF related to language of test administration in the MMSE. More attention needs to be paid to the specific criteria used to determine whether an item has DIF, not just the technique used to identify DIF.

Conditional Poisson models: a flexible alternative to conditional logistic case cross-over analysis.

PubMed

Armstrong, Ben G; Gasparrini, Antonio; Tobias, Aurelio

2014-11-24

The time stratified case cross-over approach is a popular alternative to conventional time series regression for analysing associations between time series of environmental exposures (air pollution, weather) and counts of health outcomes. These are almost always analyzed using conditional logistic regression on data expanded to case-control (case crossover) format, but this has some limitations. In particular adjusting for overdispersion and auto-correlation in the counts is not possible. It has been established that a Poisson model for counts with stratum indicators gives identical estimates to those from conditional logistic regression and does not have these limitations, but it is little used, probably because of the overheads in estimating many stratum parameters. The conditional Poisson model avoids estimating stratum parameters by conditioning on the total event count in each stratum, thus simplifying the computing and increasing the number of strata for which fitting is feasible compared with the standard unconditional Poisson model. Unlike the conditional logistic model, the conditional Poisson model does not require expanding the data, and can adjust for overdispersion and auto-correlation. It is available in Stata, R, and other packages. By applying to some real data and using simulations, we demonstrate that conditional Poisson models were simpler to code and shorter to run than are conditional logistic analyses and can be fitted to larger data sets than possible with standard Poisson models. Allowing for overdispersion or autocorrelation was possible with the conditional Poisson model but when not required this model gave identical estimates to those from conditional logistic regression. Conditional Poisson regression models provide an alternative to case crossover analysis of stratified time series data with some advantages. The conditional Poisson model can also be used in other contexts in which primary control for confounding is by fine stratification.

Use of generalized ordered logistic regression for the analysis of multidrug resistance data.

PubMed

Agga, Getahun E; Scott, H Morgan

2015-10-01

Statistical analysis of antimicrobial resistance data largely focuses on individual antimicrobial's binary outcome (susceptible or resistant). However, bacteria are becoming increasingly multidrug resistant (MDR). Statistical analysis of MDR data is mostly descriptive often with tabular or graphical presentations. Here we report the applicability of generalized ordinal logistic regression model for the analysis of MDR data. A total of 1,152 Escherichia coli, isolated from the feces of weaned pigs experimentally supplemented with chlortetracycline (CTC) and copper, were tested for susceptibilities against 15 antimicrobials and were binary classified into resistant or susceptible. The 15 antimicrobial agents tested were grouped into eight different antimicrobial classes. We defined MDR as the number of antimicrobial classes to which E. coli isolates were resistant ranging from 0 to 8. Proportionality of the odds assumption of the ordinal logistic regression model was violated only for the effect of treatment period (pre-treatment, during-treatment and post-treatment); but not for the effect of CTC or copper supplementation. Subsequently, a partially constrained generalized ordinal logistic model was built that allows for the effect of treatment period to vary while constraining the effects of treatment (CTC and copper supplementation) to be constant across the levels of MDR classes. Copper (Proportional Odds Ratio [Prop OR]=1.03; 95% CI=0.73-1.47) and CTC (Prop OR=1.1; 95% CI=0.78-1.56) supplementation were not significantly associated with the level of MDR adjusted for the effect of treatment period. MDR generally declined over the trial period. In conclusion, generalized ordered logistic regression can be used for the analysis of ordinal data such as MDR data when the proportionality assumptions for ordered logistic regression are violated. Published by Elsevier B.V.

Artificial neural networks predict the incidence of portosplenomesenteric venous thrombosis in patients with acute pancreatitis.

PubMed

Fei, Y; Hu, J; Li, W-Q; Wang, W; Zong, G-Q

2017-03-01

Essentials Predicting the occurrence of portosplenomesenteric vein thrombosis (PSMVT) is difficult. We studied 72 patients with acute pancreatitis. Artificial neural networks modeling was more accurate than logistic regression in predicting PSMVT. Additional predictive factors may be incorporated into artificial neural networks. Objective To construct and validate artificial neural networks (ANNs) for predicting the occurrence of portosplenomesenteric venous thrombosis (PSMVT) and compare the predictive ability of the ANNs with that of logistic regression. Methods The ANNs and logistic regression modeling were constructed using simple clinical and laboratory data of 72 acute pancreatitis (AP) patients. The ANNs and logistic modeling were first trained on 48 randomly chosen patients and validated on the remaining 24 patients. The accuracy and the performance characteristics were compared between these two approaches by SPSS17.0 software. Results The training set and validation set did not differ on any of the 11 variables. After training, the back propagation network training error converged to 1 × 10 -20 , and it retained excellent pattern recognition ability. When the ANNs model was applied to the validation set, it revealed a sensitivity of 80%, specificity of 85.7%, a positive predictive value of 77.6% and negative predictive value of 90.7%. The accuracy was 83.3%. Differences could be found between ANNs modeling and logistic regression modeling in these parameters (10.0% [95% CI, -14.3 to 34.3%], 14.3% [95% CI, -8.6 to 37.2%], 15.7% [95% CI, -9.9 to 41.3%], 11.8% [95% CI, -8.2 to 31.8%], 22.6% [95% CI, -1.9 to 47.1%], respectively). When ANNs modeling was used to identify PSMVT, the area under receiver operating characteristic curve was 0.849 (95% CI, 0.807-0.901), which demonstrated better overall properties than logistic regression modeling (AUC = 0.716) (95% CI, 0.679-0.761). Conclusions ANNs modeling was a more accurate tool than logistic regression in predicting the occurrence of PSMVT following AP. More clinical factors or biomarkers may be incorporated into ANNs modeling to improve its predictive ability. © 2016 International Society on Thrombosis and Haemostasis.

PREDICTION OF MALIGNANT BREAST LESIONS FROM MRI FEATURES: A COMPARISON OF ARTIFICIAL NEURAL NETWORK AND LOGISTIC REGRESSION TECHNIQUES

PubMed Central

McLaren, Christine E.; Chen, Wen-Pin; Nie, Ke; Su, Min-Ying

2009-01-01

Rationale and Objectives Dynamic contrast enhanced MRI (DCE-MRI) is a clinical imaging modality for detection and diagnosis of breast lesions. Analytical methods were compared for diagnostic feature selection and performance of lesion classification to differentiate between malignant and benign lesions in patients. Materials and Methods The study included 43 malignant and 28 benign histologically-proven lesions. Eight morphological parameters, ten gray level co-occurrence matrices (GLCM) texture features, and fourteen Laws’ texture features were obtained using automated lesion segmentation and quantitative feature extraction. Artificial neural network (ANN) and logistic regression analysis were compared for selection of the best predictors of malignant lesions among the normalized features. Results Using ANN, the final four selected features were compactness, energy, homogeneity, and Law_LS, with area under the receiver operating characteristic curve (AUC) = 0.82, and accuracy = 0.76. The diagnostic performance of these 4-features computed on the basis of logistic regression yielded AUC = 0.80 (95% CI, 0.688 to 0.905), similar to that of ANN. The analysis also shows that the odds of a malignant lesion decreased by 48% (95% CI, 25% to 92%) for every increase of 1 SD in the Law_LS feature, adjusted for differences in compactness, energy, and homogeneity. Using logistic regression with z-score transformation, a model comprised of compactness, NRL entropy, and gray level sum average was selected, and it had the highest overall accuracy of 0.75 among all models, with AUC = 0.77 (95% CI, 0.660 to 0.880). When logistic modeling of transformations using the Box-Cox method was performed, the most parsimonious model with predictors, compactness and Law_LS, had an AUC of 0.79 (95% CI, 0.672 to 0.898). Conclusion The diagnostic performance of models selected by ANN and logistic regression was similar. The analytic methods were found to be roughly equivalent in terms of predictive ability when a small number of variables were chosen. The robust ANN methodology utilizes a sophisticated non-linear model, while logistic regression analysis provides insightful information to enhance interpretation of the model features. PMID:19409817

Logistic regression analysis of factors associated with avascular necrosis of the femoral head following femoral neck fractures in middle-aged and elderly patients.

PubMed

Ai, Zi-Sheng; Gao, You-Shui; Sun, Yuan; Liu, Yue; Zhang, Chang-Qing; Jiang, Cheng-Hua

2013-03-01

Risk factors for femoral neck fracture-induced avascular necrosis of the femoral head have not been elucidated clearly in middle-aged and elderly patients. Moreover, the high incidence of screw removal in China and its effect on the fate of the involved femoral head require statistical methods to reflect their intrinsic relationship. Ninety-nine patients older than 45 years with femoral neck fracture were treated by internal fixation between May 1999 and April 2004. Descriptive analysis, interaction analysis between associated factors, single factor logistic regression, multivariate logistic regression, and detailed interaction analysis were employed to explore potential relationships among associated factors. Avascular necrosis of the femoral head was found in 15 cases (15.2 %). Age × the status of implants (removal vs. maintenance) and gender × the timing of reduction were interactive according to two-factor interactive analysis. Age, the displacement of fractures, the quality of reduction, and the status of implants were found to be significant factors in single factor logistic regression analysis. Age, age × the status of implants, and the quality of reduction were found to be significant factors in multivariate logistic regression analysis. In fine interaction analysis after multivariate logistic regression analysis, implant removal was the most important risk factor for avascular necrosis in 56-to-85-year-old patients, with a risk ratio of 26.00 (95 % CI = 3.076-219.747). The middle-aged and elderly have less incidence of avascular necrosis of the femoral head following femoral neck fractures treated by cannulated screws. The removal of cannulated screws can induce a significantly high incidence of avascular necrosis of the femoral head in elderly patients, while a high-quality reduction is helpful to reduce avascular necrosis.

Regression Simulation Model. Appendix X. Users Manual,

DTIC Science & Technology

1981-03-01

change as the prediction equations become refined. Whereas no notice will be provided when the changes are made, the programs will be modified such that...NATIONAL BUREAU Of STANDARDS 1963 A ___,_ __ _ __ _ . APPENDIX X ( R4/ EGRESSION IMULATION ’jDEL. Ape’A ’) 7 USERS MANUA submitted to The Great River...regression analysis and to establish a prediction equation (model). The prediction equation contains the partial regression coefficients (B-weights) which

Objective Lightning Forecasting at Kennedy Space Center/Cape Canaveral Air Force Station using Cloud-to-Ground Lightning Surveillance System Data

NASA Technical Reports Server (NTRS)

Lambert, Winifred; Wheeler, Mark

2004-01-01

The 45th Weather Squadron (45 WS) forecasters at Cape Canaveral Air Force Station (CCAFS) in Florida include a probability of thunderstorm occurrence in their daily morning briefings. This information is used by personnel involved in determining the possibility of violating Launch Commit Criteria, evaluating Flight Rules for the Space Shuttle, and daily planning for ground operation activities on Kennedy Space Center (KSC)/CCAFS. Much of the current lightning probability forecast is based on a subjective analysis of model and observational data. The forecasters requested that a lightning probability forecast tool based on statistical analysis of historical warm-season (May - September) data be developed in order to increase the objectivity of the daily thunderstorm probability forecast. The tool is a set of statistical lightning forecast equations that provide a lightning occurrence probability for the day by 1100 UTC (0700 EDT) during the warm season. This study used 15 years (1989-2003) of warm season data to develop the objective forecast equations. The local CCAFS 1000 UTC sounding was used to calculate stability parameters for equation predictors. The Cloud-to-Ground Lightning Surveillance System (CGLSS) data were used to determine lightning occurrence for each day. The CGLSS data have been found to be more reliable indicators of lightning in the area than surface observations through local informal analyses. This work was based on the results from two earlier research projects. Everitt (1999) used surface observations and rawinsonde data to develop logistic regression equations that forecast the daily thunderstorm probability at CCAFS. The Everitt (1999) equations showed an improvement in skill over the Neumann-Pfeffer thunderstorm index (Neumann 1971), which uses multiple linear regression, and also persistence and climatology forecasts. Lericos et al. (2002) developed lightning distributions over the Florida peninsula based on specific flow regimes. The flow regimes were inferred from the average wind direction in the 1000-700 mb layer at Miami (MIA), Tampa (TBW), and Jacksonville (JAX), Florida, and the lightning data were from the National Lightning Detection Network. The results suggested that the daily flow regime may be an important predictor of lightning occurrence on KSC/CCAFS.

Drawing Nomograms with R: applications to categorical outcome and survival data.

PubMed

Zhang, Zhongheng; Kattan, Michael W

2017-05-01

Outcome prediction is a major task in clinical medicine. The standard approach to this work is to collect a variety of predictors and build a model of appropriate type. The model is a mathematical equation that connects the outcome of interest with the predictors. A new patient with given clinical characteristics can be predicted for outcome with this model. However, the equation describing the relationship between predictors and outcome is often complex and the computation requires software for practical use. There is another method called nomogram which is a graphical calculating device allowing an approximate graphical computation of a mathematical function. In this article, we describe how to draw nomograms for various outcomes with nomogram() function. Binary outcome is fit by logistic regression model and the outcome of interest is the probability of the event of interest. Ordinal outcome variable is also discussed. Survival analysis can be fit with parametric model to fully describe the distributions of survival time. Statistics such as the median survival time, survival probability up to a specific time point are taken as the outcome of interest.

Relationship between long working hours and depression in two working populations: a structural equation model approach.

PubMed

Amagasa, Takashi; Nakayama, Takeo

2012-07-01

To test the hypothesis that relationship reported between long working hours and depression was inconsistent in previous studies because job demand was treated as a confounder. Structural equation modeling was used to construct five models, using work-related factors and depressive mood scale obtained from 218 clerical workers, to test for goodness of fit and was externally validated with data obtained from 1160 sales workers. Multiple logistic regression analysis was also performed. The model that showed that long working hours increased depression risk when job demand was regarded as an intermediate variable was the best fitted model (goodness-of-fit index/root-mean-square error of approximation: 0.981 to 0.996/0.042 to 0.044). The odds ratio for depression risk with work that was high demand and 60 hours or more per week was estimated at 2 to 4 versus work that was low demand and less than 60 hours per week. Long working hours increased depression risk, with job demand being an intermediate variable.

Rank-Optimized Logistic Matrix Regression toward Improved Matrix Data Classification.

PubMed

Zhang, Jianguang; Jiang, Jianmin

2018-02-01

While existing logistic regression suffers from overfitting and often fails in considering structural information, we propose a novel matrix-based logistic regression to overcome the weakness. In the proposed method, 2D matrices are directly used to learn two groups of parameter vectors along each dimension without vectorization, which allows the proposed method to fully exploit the underlying structural information embedded inside the 2D matrices. Further, we add a joint [Formula: see text]-norm on two parameter matrices, which are organized by aligning each group of parameter vectors in columns. This added co-regularization term has two roles-enhancing the effect of regularization and optimizing the rank during the learning process. With our proposed fast iterative solution, we carried out extensive experiments. The results show that in comparison to both the traditional tensor-based methods and the vector-based regression methods, our proposed solution achieves better performance for matrix data classifications.

Detecting DIF in Polytomous Items Using MACS, IRT and Ordinal Logistic Regression

ERIC Educational Resources Information Center

Elosua, Paula; Wells, Craig

2013-01-01

The purpose of the present study was to compare the Type I error rate and power of two model-based procedures, the mean and covariance structure model (MACS) and the item response theory (IRT), and an observed-score based procedure, ordinal logistic regression, for detecting differential item functioning (DIF) in polytomous items. A simulation…

Accuracy of Bayes and Logistic Regression Subscale Probabilities for Educational and Certification Tests

ERIC Educational Resources Information Center

Rudner, Lawrence

2016-01-01

In the machine learning literature, it is commonly accepted as fact that as calibration sample sizes increase, Naïve Bayes classifiers initially outperform Logistic Regression classifiers in terms of classification accuracy. Applied to subtests from an on-line final examination and from a highly regarded certification examination, this study shows…

Comparing Linear Discriminant Function with Logistic Regression for the Two-Group Classification Problem.

ERIC Educational Resources Information Center

Fan, Xitao; Wang, Lin

The Monte Carlo study compared the performance of predictive discriminant analysis (PDA) and that of logistic regression (LR) for the two-group classification problem. Prior probabilities were used for classification, but the cost of misclassification was assumed to be equal. The study used a fully crossed three-factor experimental design (with…

Effects of Social Class and School Conditions on Educational Enrollment and Achievement of Boys and Girls in Rural Viet Nam

ERIC Educational Resources Information Center

Nguyen, Phuong L.

2006-01-01

This study examines the effects of parental SES, school quality, and community factors on children's enrollment and achievement in rural areas in Viet Nam, using logistic regression and ordered logistic regression. Multivariate analysis reveals significant differences in educational enrollment and outcomes by level of household expenditures and…

School Exits in the Milwaukee Parental Choice Program: Evidence of a Marketplace?

ERIC Educational Resources Information Center

Ford, Michael

2011-01-01

This article examines whether the large number of school exits from the Milwaukee school voucher program is evidence of a marketplace. Two logistic regression and multinomial logistic regression models tested the relation between the inability to draw large numbers of voucher students and the ability for a private school to remain viable. Data on…

Hierarchical Bayesian Logistic Regression to forecast metabolic control in type 2 DM patients.

PubMed

Dagliati, Arianna; Malovini, Alberto; Decata, Pasquale; Cogni, Giulia; Teliti, Marsida; Sacchi, Lucia; Cerra, Carlo; Chiovato, Luca; Bellazzi, Riccardo

2016-01-01

In this work we present our efforts in building a model able to forecast patients' changes in clinical conditions when repeated measurements are available. In this case the available risk calculators are typically not applicable. We propose a Hierarchical Bayesian Logistic Regression model, which allows taking into account individual and population variability in model parameters estimate. The model is used to predict metabolic control and its variation in type 2 diabetes mellitus. In particular we have analyzed a population of more than 1000 Italian type 2 diabetic patients, collected within the European project Mosaic. The results obtained in terms of Matthews Correlation Coefficient are significantly better than the ones gathered with standard logistic regression model, based on data pooling.

An empirical study of statistical properties of variance partition coefficients for multi-level logistic regression models

USGS Publications Warehouse

Li, Ji; Gray, B.R.; Bates, D.M.

2008-01-01

Partitioning the variance of a response by design levels is challenging for binomial and other discrete outcomes. Goldstein (2003) proposed four definitions for variance partitioning coefficients (VPC) under a two-level logistic regression model. In this study, we explicitly derived formulae for multi-level logistic regression model and subsequently studied the distributional properties of the calculated VPCs. Using simulations and a vegetation dataset, we demonstrated associations between different VPC definitions, the importance of methods for estimating VPCs (by comparing VPC obtained using Laplace and penalized quasilikehood methods), and bivariate dependence between VPCs calculated at different levels. Such an empirical study lends an immediate support to wider applications of VPC in scientific data analysis.

Model building strategy for logistic regression: purposeful selection.

PubMed

Zhang, Zhongheng

2016-03-01

Logistic regression is one of the most commonly used models to account for confounders in medical literature. The article introduces how to perform purposeful selection model building strategy with R. I stress on the use of likelihood ratio test to see whether deleting a variable will have significant impact on model fit. A deleted variable should also be checked for whether it is an important adjustment of remaining covariates. Interaction should be checked to disentangle complex relationship between covariates and their synergistic effect on response variable. Model should be checked for the goodness-of-fit (GOF). In other words, how the fitted model reflects the real data. Hosmer-Lemeshow GOF test is the most widely used for logistic regression model.

A Common Mechanism for Resistance to Oxime Reactivation of Acetylcholinesterase Inhibited by Organophosphorus Compounds

DTIC Science & Technology

2013-01-01

application of the Hammett equation with the constants rph in the chemistry of organophosphorus compounds, Russ. Chem. Rev. 38 (1969) 795–811. [13...of oximes and OP compounds and the ability of oximes to reactivate OP- inhibited AChE. Multiple linear regression equations were analyzed using...phosphonate pairs, 21 oxime/ phosphoramidate pairs and 12 oxime/phosphate pairs. The best linear regression equation resulting from multiple regression anal

Estimating Flow-Duration and Low-Flow Frequency Statistics for Unregulated Streams in Oregon

USGS Publications Warehouse

Risley, John; Stonewall, Adam J.; Haluska, Tana

2008-01-01

Flow statistical datasets, basin-characteristic datasets, and regression equations were developed to provide decision makers with surface-water information needed for activities such as water-quality regulation, water-rights adjudication, biological habitat assessment, infrastructure design, and water-supply planning and management. The flow statistics, which included annual and monthly period of record flow durations (5th, 10th, 25th, 50th, and 95th percent exceedances) and annual and monthly 7-day, 10-year (7Q10) and 7-day, 2-year (7Q2) low flows, were computed at 466 streamflow-gaging stations at sites with unregulated flow conditions throughout Oregon and adjacent areas of neighboring States. Regression equations, created from the flow statistics and basin characteristics of the stations, can be used to estimate flow statistics at ungaged stream sites in Oregon. The study area was divided into 10 regression modeling regions based on ecological, topographic, geologic, hydrologic, and climatic criteria. In total, 910 annual and monthly regression equations were created to predict the 7 flow statistics in the 10 regions. Equations to predict the five flow-duration exceedance percentages and the two low-flow frequency statistics were created with Ordinary Least Squares and Generalized Least Squares regression, respectively. The standard errors of estimate of the equations created to predict the 5th and 95th percent exceedances had medians of 42.4 and 64.4 percent, respectively. The standard errors of prediction of the equations created to predict the 7Q2 and 7Q10 low-flow statistics had medians of 51.7 and 61.2 percent, respectively. Standard errors for regression equations for sites in western Oregon were smaller than those in eastern Oregon partly because of a greater density of available streamflow-gaging stations in western Oregon than eastern Oregon. High-flow regression equations (such as the 5th and 10th percent exceedances) also generally were more accurate than the low-flow regression equations (such as the 95th percent exceedance and 7Q10 low-flow statistic). The regression equations predict unregulated flow conditions in Oregon. Flow estimates need to be adjusted if they are used at ungaged sites that are regulated by reservoirs or affected by water-supply and agricultural withdrawals if actual flow conditions are of interest. The regression equations are installed in the USGS StreamStats Web-based tool (http://water.usgs.gov/osw/streamstats/index.html, accessed July 16, 2008). StreamStats provides users with a set of annual and monthly flow-duration and low-flow frequency estimates for ungaged sites in Oregon in addition to the basin characteristics for the sites. Prediction intervals at the 90-percent confidence level also are automatically computed.

Application of conditional moment tests to model checking for generalized linear models.

PubMed

Pan, Wei

2002-06-01

Generalized linear models (GLMs) are increasingly being used in daily data analysis. However, model checking for GLMs with correlated discrete response data remains difficult. In this paper, through a case study on marginal logistic regression using a real data set, we illustrate the flexibility and effectiveness of using conditional moment tests (CMTs), along with other graphical methods, to do model checking for generalized estimation equation (GEE) analyses. Although CMTs provide an array of powerful diagnostic tests for model checking, they were originally proposed in the econometrics literature and, to our knowledge, have never been applied to GEE analyses. CMTs cover many existing tests, including the (generalized) score test for an omitted covariate, as special cases. In summary, we believe that CMTs provide a class of useful model checking tools.

Recent im/migration to Canada linked to unmet health needs among sex workers in Vancouver, Canada: Findings of a longitudinal study.

PubMed

Sou, Julie; Goldenberg, Shira M; Duff, Putu; Nguyen, Paul; Shoveller, Jean; Shannon, Kate

2017-05-01

Despite universal health care in Canada, sex workers (SWs) and im/migrants experience suboptimal health care access. In this analysis, we examined the correlates of unmet health needs among SWs in Metro Vancouver over time. Data from a longitudinal cohort of women SWs (An Evaluation of Sex Workers Health Access [AESHA]) were used. Of 742 SWs, 25.5% reported unmet health needs at least once over the 4-year study period. In multivariable logistic regression using generalized estimating equations, recent im/migration had the strongest impact on unmet health needs; long-term im/migration, policing, and trauma were also important determinants. Legal and social supports to promote im/migrant SWs' access to health care are recommended.

Father-son attachment and sexual partner orientation in Taiwan.

PubMed

Lung, For-Wey; Shu, Bih-Ching

2007-01-01

The topic of homosexual adjustment problems has never been explored in Taiwan. The aim of this study was to investigate the role of parental bonding in the adjustment problems of homosexuals. A total of 51 young homosexual males, 100 nonhomosexual personnel with adjustment disorder, and 124 controls were administered the Parental Bonding Instrument, the Eysenck Personality Questionnaire, and the Chinese Health Questionnaire. The final parsimonious logistic regression and structural equation modeling showed paternal attachment, especially paternal overprotection, to be a predisposing factor in the development of homosexuality. Paternal attachment, introversion, and neurotic characteristics were key factors in the development of homosexuals. In particular, paternal overprotection played the most important role in the developmental process of male homosexuals. This study can be used as a reference for clinical personnel in caring for male homosexuals.

A social ecological assessment of physical activity among urban adolescents.

PubMed

Yan, Alice Fang; Voorhees, Carolyn C; Beck, Kenneth H; Wang, Min Qi

2014-05-01

To examine the physical, social and temporal contexts of physical activity, as well as sex variations of the associations among 314 urban adolescents. Three-day physical activity recall measured contextual information of physical activities. Logistic regressions and generalized estimating equation models examined associations among physical activity types and contexts, and sex differences. Active transportation was the most common physical activity. Home/neighborhood and school were the most common physical activity locations. School was the main location for organized physical activity. Boys spent more time on recreational physical activity, regardless of the social context, compared to girls. The average physical activity level was significantly lower for girls than for boys after school. Physical activity promotion interventions need to target physical activity environments and social contexts in a sex-specific manner.

Regression Equations for Monthly and Annual Mean and Selected Percentile Streamflows for Ungaged Rivers in Maine

USGS Publications Warehouse

Dudley, Robert W.

2015-12-03

The largest average errors of prediction are associated with regression equations for the lowest streamflows derived for months during which the lowest streamflows of the year occur (such as the 5 and 1 monthly percentiles for August and September). The regression equations have been derived on the basis of streamflow and basin characteristics data for unregulated, rural drainage basins without substantial streamflow or drainage modifications (for example, diversions and (or) regulation by dams or reservoirs, tile drainage, irrigation, channelization, and impervious paved surfaces), therefore using the equations for regulated or urbanized basins with substantial streamflow or drainage modifications will yield results of unknown error. Input basin characteristics derived using techniques or datasets other than those documented in this report or using values outside the ranges used to develop these regression equations also will yield results of unknown error.

Modeling the rheological behavior of thermosonic extracted guava, pomelo, and soursop juice concentrates at different concentration and temperature using a new combination model

PubMed Central

Abdullah, Norazlin; Yusof, Yus A.; Talib, Rosnita A.

2017-01-01

Abstract This study has modeled the rheological behavior of thermosonic extracted pink‐fleshed guava, pink‐fleshed pomelo, and soursop juice concentrates at different concentrations and temperatures. The effects of concentration on consistency coefficient (K) and flow behavior index (n) of the fruit juice concentrates was modeled using a master curve which utilized the concentration‐temperature shifting to allow a general prediction of rheological behaviors covering a wide concentration. For modeling the effects of temperature on K and n, the integration of two functions from the Arrhenius and logistic sigmoidal growth equations has provided a new model which gave better description of the properties. It also alleviated the problems of negative region when using the Arrhenius model alone. The fitted regression using this new model has improved coefficient of determination, R 2 values above 0.9792 as compared to using the Arrhenius and logistic sigmoidal models alone, which presented minimum R 2 of 0.6243 and 0.9440, respectively. Practical applications In general, juice concentrate is a better form of food for transportation, preservation, and ingredient. Models are necessary to predict the effects of processing factors such as concentration and temperature on the rheological behavior of juice concentrates. The modeling approach allows prediction of behaviors and determination of processing parameters. The master curve model introduced in this study simplifies and generalized rheological behavior of juice concentrates over a wide range of concentration when temperature factor is insignificant. The proposed new mathematical model from the combination of the Arrhenius and logistic sigmoidal growth models has improved and extended description of rheological properties of fruit juice concentrates. It also solved problems of negative values of consistency coefficient and flow behavior index prediction using existing model, the Arrhenius equation. These rheological data modeling provide good information for the juice processing and equipment manufacturing needs. PMID:29479123

Comparative evaluation of urban storm water quality models

NASA Astrophysics Data System (ADS)

Vaze, J.; Chiew, Francis H. S.

2003-10-01

The estimation of urban storm water pollutant loads is required for the development of mitigation and management strategies to minimize impacts to receiving environments. Event pollutant loads are typically estimated using either regression equations or "process-based" water quality models. The relative merit of using regression models compared to process-based models is not clear. A modeling study is carried out here to evaluate the comparative ability of the regression equations and process-based water quality models to estimate event diffuse pollutant loads from impervious surfaces. The results indicate that, once calibrated, both the regression equations and the process-based model can estimate event pollutant loads satisfactorily. In fact, the loads estimated using the regression equation as a function of rainfall intensity and runoff rate are better than the loads estimated using the process-based model. Therefore, if only estimates of event loads are required, regression models should be used because they are simpler and require less data compared to process-based models.

Assessing landslide susceptibility by statistical data analysis and GIS: the case of Daunia (Apulian Apennines, Italy)

NASA Astrophysics Data System (ADS)

Ceppi, C.; Mancini, F.; Ritrovato, G.

2009-04-01

This study aim at the landslide susceptibility mapping within an area of the Daunia (Apulian Apennines, Italy) by a multivariate statistical method and data manipulation in a Geographical Information System (GIS) environment. Among the variety of existing statistical data analysis techniques, the logistic regression was chosen to produce a susceptibility map all over an area where small settlements are historically threatened by landslide phenomena. By logistic regression a best fitting between the presence or absence of landslide (dependent variable) and the set of independent variables is performed on the basis of a maximum likelihood criterion, bringing to the estimation of regression coefficients. The reliability of such analysis is therefore due to the ability to quantify the proneness to landslide occurrences by the probability level produced by the analysis. The inventory of dependent and independent variables were managed in a GIS, where geometric properties and attributes have been translated into raster cells in order to proceed with the logistic regression by means of SPSS (Statistical Package for the Social Sciences) package. A landslide inventory was used to produce the bivariate dependent variable whereas the independent set of variable concerned with slope, aspect, elevation, curvature, drained area, lithology and land use after their reductions to dummy variables. The effect of independent parameters on landslide occurrence was assessed by the corresponding coefficient in the logistic regression function, highlighting a major role played by the land use variable in determining occurrence and distribution of phenomena. Once the outcomes of the logistic regression are determined, data are re-introduced in the GIS to produce a map reporting the proneness to landslide as predicted level of probability. As validation of results and regression model a cell-by-cell comparison between the susceptibility map and the initial inventory of landslide events was performed and an agreement at 75% level achieved.

Determination of riverbank erosion probability using Locally Weighted Logistic Regression

NASA Astrophysics Data System (ADS)

Ioannidou, Elena; Flori, Aikaterini; Varouchakis, Emmanouil A.; Giannakis, Georgios; Vozinaki, Anthi Eirini K.; Karatzas, George P.; Nikolaidis, Nikolaos

2015-04-01

Riverbank erosion is a natural geomorphologic process that affects the fluvial environment. The most important issue concerning riverbank erosion is the identification of the vulnerable locations. An alternative to the usual hydrodynamic models to predict vulnerable locations is to quantify the probability of erosion occurrence. This can be achieved by identifying the underlying relations between riverbank erosion and the geomorphological or hydrological variables that prevent or stimulate erosion. Thus, riverbank erosion can be determined by a regression model using independent variables that are considered to affect the erosion process. The impact of such variables may vary spatially, therefore, a non-stationary regression model is preferred instead of a stationary equivalent. Locally Weighted Regression (LWR) is proposed as a suitable choice. This method can be extended to predict the binary presence or absence of erosion based on a series of independent local variables by using the logistic regression model. It is referred to as Locally Weighted Logistic Regression (LWLR). Logistic regression is a type of regression analysis used for predicting the outcome of a categorical dependent variable (e.g. binary response) based on one or more predictor variables. The method can be combined with LWR to assign weights to local independent variables of the dependent one. LWR allows model parameters to vary over space in order to reflect spatial heterogeneity. The probabilities of the possible outcomes are modelled as a function of the independent variables using a logistic function. Logistic regression measures the relationship between a categorical dependent variable and, usually, one or several continuous independent variables by converting the dependent variable to probability scores. Then, a logistic regression is formed, which predicts success or failure of a given binary variable (e.g. erosion presence or absence) for any value of the independent variables. The erosion occurrence probability can be calculated in conjunction with the model deviance regarding the independent variables tested. The most straightforward measure for goodness of fit is the G statistic. It is a simple and effective way to study and evaluate the Logistic Regression model efficiency and the reliability of each independent variable. The developed statistical model is applied to the Koiliaris River Basin on the island of Crete, Greece. Two datasets of river bank slope, river cross-section width and indications of erosion were available for the analysis (12 and 8 locations). Two different types of spatial dependence functions, exponential and tricubic, were examined to determine the local spatial dependence of the independent variables at the measurement locations. The results show a significant improvement when the tricubic function is applied as the erosion probability is accurately predicted at all eight validation locations. Results for the model deviance show that cross-section width is more important than bank slope in the estimation of erosion probability along the Koiliaris riverbanks. The proposed statistical model is a useful tool that quantifies the erosion probability along the riverbanks and can be used to assist managing erosion and flooding events. Acknowledgements This work is part of an on-going THALES project (CYBERSENSORS - High Frequency Monitoring System for Integrated Water Resources Management of Rivers). The project has been co-financed by the European Union (European Social Fund - ESF) and Greek national funds through the Operational Program "Education and Lifelong Learning" of the National Strategic Reference Framework (NSRF) - Research Funding Program: THALES. Investing in knowledge society through the European Social Fund.

Statistical summary of selected physical, chemical, and toxicity characteristics and estimates of annual constituent loads in urban stormwater, Maricopa County, Arizona

USGS Publications Warehouse

Fossum, Kenneth D.; O'Day, Christie M.; Wilson, Barbara J.; Monical, Jim E.

2001-01-01

Stormwater and streamflow in Maricopa County were monitored to (1) describe the physical, chemical, and toxicity characteristics of stormwater from areas having different land uses, (2) describe the physical, chemical, and toxicity characteristics of streamflow from areas that receive urban stormwater, and (3) estimate constituent loads in stormwater. Urban stormwater and streamflow had similar ranges in most constituent concentrations. The mean concentration of dissolved solids in urban stormwater was lower than in streamflow from the Salt River and Indian Bend Wash. Urban stormwater, however, had a greater chemical oxygen demand and higher concentrations of most nutrients. Mean seasonal loads and mean annual loads of 11 constituents and volumes of runoff were estimated for municipalities in the metropolitan Phoenix area, Arizona, by adjusting regional regression equations of loads. This adjustment procedure uses the original regional regression equation and additional explanatory variables that were not included in the original equation. The adjusted equations had standard errors that ranged from 161 to 196 percent. The large standard errors of the prediction result from the large variability of the constituent concentration data used in the regression analysis. Adjustment procedures produced unsatisfactory results for nine of the regressions?suspended solids, dissolved solids, total phosphorus, dissolved phosphorus, total recoverable cadmium, total recoverable copper, total recoverable lead, total recoverable zinc, and storm runoff. These equations had no consistent direction of bias and no other additional explanatory variables correlated with the observed loads. A stepwise-multiple regression or a three-variable regression (total storm rainfall, drainage area, and impervious area) and local data were used to develop local regression equations for these nine constituents. These equations had standard errors from 15 to 183 percent.

Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat—Turkey)

NASA Astrophysics Data System (ADS)

Yilmaz, Işık

2009-06-01

The purpose of this study is to compare the landslide susceptibility mapping methods of frequency ratio (FR), logistic regression and artificial neural networks (ANN) applied in the Kat County (Tokat—Turkey). Digital elevation model (DEM) was first constructed using GIS software. Landslide-related factors such as geology, faults, drainage system, topographical elevation, slope angle, slope aspect, topographic wetness index (TWI) and stream power index (SPI) were used in the landslide susceptibility analyses. Landslide susceptibility maps were produced from the frequency ratio, logistic regression and neural networks models, and they were then compared by means of their validations. The higher accuracies of the susceptibility maps for all three models were obtained from the comparison of the landslide susceptibility maps with the known landslide locations. However, respective area under curve (AUC) values of 0.826, 0.842 and 0.852 for frequency ratio, logistic regression and artificial neural networks showed that the map obtained from ANN model is more accurate than the other models, accuracies of all models can be evaluated relatively similar. The results obtained in this study also showed that the frequency ratio model can be used as a simple tool in assessment of landslide susceptibility when a sufficient number of data were obtained. Input process, calculations and output process are very simple and can be readily understood in the frequency ratio model, however logistic regression and neural networks require the conversion of data to ASCII or other formats. Moreover, it is also very hard to process the large amount of data in the statistical package.

Objective Lightning Probability Forecasting for Kennedy Space Center and Cape Canaveral Air Force Station, Phase III

NASA Technical Reports Server (NTRS)

Crawford, Winifred C.

2010-01-01

The AMU created new logistic regression equations in an effort to increase the skill of the Objective Lightning Forecast Tool developed in Phase II (Lambert 2007). One equation was created for each of five sub-seasons based on the daily lightning climatology instead of by month as was done in Phase II. The assumption was that these equations would capture the physical attributes that contribute to thunderstorm formation more so than monthly equations. However, the SS values in Section 5.3.2 showed that the Phase III equations had worse skill than the Phase II equations and, therefore, will not be transitioned into operations. The current Objective Lightning Forecast Tool developed in Phase II will continue to be used operationally in MIDDS. Three warm seasons were added to the Phase II dataset to increase the POR from 17 to 20 years (1989-2008), and data for October were included since the daily climatology showed lightning occurrence extending into that month. None of the three methods tested to determine the start of the subseason in each individual year were able to discern the start dates with consistent accuracy. Therefore, the start dates were determined by the daily climatology shown in Figure 10 and were the same in every year. The procedures used to create the predictors and develop the equations were identical to those in Phase II. The equations were made up of one to three predictors. TI and the flow regime probabilities were the top predictors followed by 1-day persistence, then VT and Ll. Each equation outperformed four other forecast methods by 7-57% using the verification dataset, but the new equations were outperformed by the Phase II equations in every sub-season. The reason for the degradation may be due to the fact that the same sub-season start dates were used in every year. It is likely there was overlap of sub-season days at the beginning and end of each defined sub-season in each individual year, which could very well affect equation performance.

A Comparison of Logistic Regression, Neural Networks, and Classification Trees Predicting Success of Actuarial Students

ERIC Educational Resources Information Center

Schumacher, Phyllis; Olinsky, Alan; Quinn, John; Smith, Richard

2010-01-01

The authors extended previous research by 2 of the authors who conducted a study designed to predict the successful completion of students enrolled in an actuarial program. They used logistic regression to determine the probability of an actuarial student graduating in the major or dropping out. They compared the results of this study with those…

Logistic regression accuracy across different spatial and temporal scales for a wide-ranging species, the marbled murrelet

Treesearch

Carolyn B. Meyer; Sherri L. Miller; C. John Ralph

2004-01-01

The scale at which habitat variables are measured affects the accuracy of resource selection functions in predicting animal use of sites. We used logistic regression models for a wide-ranging species, the marbled murrelet, (Brachyramphus marmoratus) in a large region in California to address how much changing the spatial or temporal scale of...

A Generalized Logistic Regression Procedure to Detect Differential Item Functioning among Multiple Groups

ERIC Educational Resources Information Center

Magis, David; Raiche, Gilles; Beland, Sebastien; Gerard, Paul

2011-01-01

We present an extension of the logistic regression procedure to identify dichotomous differential item functioning (DIF) in the presence of more than two groups of respondents. Starting from the usual framework of a single focal group, we propose a general approach to estimate the item response functions in each group and to test for the presence…

Risk Factors of Falls in Community-Dwelling Older Adults: Logistic Regression Tree Analysis

ERIC Educational Resources Information Center

Yamashita, Takashi; Noe, Douglas A.; Bailer, A. John

2012-01-01

Purpose of the Study: A novel logistic regression tree-based method was applied to identify fall risk factors and possible interaction effects of those risk factors. Design and Methods: A nationally representative sample of American older adults aged 65 years and older (N = 9,592) in the Health and Retirement Study 2004 and 2006 modules was used.…

Estimation of Logistic Regression Models in Small Samples. A Simulation Study Using a Weakly Informative Default Prior Distribution

ERIC Educational Resources Information Center

Gordovil-Merino, Amalia; Guardia-Olmos, Joan; Pero-Cebollero, Maribel

2012-01-01

In this paper, we used simulations to compare the performance of classical and Bayesian estimations in logistic regression models using small samples. In the performed simulations, conditions were varied, including the type of relationship between independent and dependent variable values (i.e., unrelated and related values), the type of variable…

Using multiple logistic regression and GIS technology to predict landslide hazard in northeast Kansas, USA

USGS Publications Warehouse

Ohlmacher, G.C.; Davis, J.C.

2003-01-01

Landslides in the hilly terrain along the Kansas and Missouri rivers in northeastern Kansas have caused millions of dollars in property damage during the last decade. To address this problem, a statistical method called multiple logistic regression has been used to create a landslide-hazard map for Atchison, Kansas, and surrounding areas. Data included digitized geology, slopes, and landslides, manipulated using ArcView GIS. Logistic regression relates predictor variables to the occurrence or nonoccurrence of landslides within geographic cells and uses the relationship to produce a map showing the probability of future landslides, given local slopes and geologic units. Results indicated that slope is the most important variable for estimating landslide hazard in the study area. Geologic units consisting mostly of shale, siltstone, and sandstone were most susceptible to landslides. Soil type and aspect ratio were considered but excluded from the final analysis because these variables did not significantly add to the predictive power of the logistic regression. Soil types were highly correlated with the geologic units, and no significant relationships existed between landslides and slope aspect. ?? 2003 Elsevier Science B.V. All rights reserved.

A Method for Calculating the Probability of Successfully Completing a Rocket Propulsion Ground Test

NASA Technical Reports Server (NTRS)

Messer, Bradley

2007-01-01

Propulsion ground test facilities face the daily challenge of scheduling multiple customers into limited facility space and successfully completing their propulsion test projects. Over the last decade NASA s propulsion test facilities have performed hundreds of tests, collected thousands of seconds of test data, and exceeded the capabilities of numerous test facility and test article components. A logistic regression mathematical modeling technique has been developed to predict the probability of successfully completing a rocket propulsion test. A logistic regression model is a mathematical modeling approach that can be used to describe the relationship of several independent predictor variables X(sub 1), X(sub 2),.., X(sub k) to a binary or dichotomous dependent variable Y, where Y can only be one of two possible outcomes, in this case Success or Failure of accomplishing a full duration test. The use of logistic regression modeling is not new; however, modeling propulsion ground test facilities using logistic regression is both a new and unique application of the statistical technique. Results from this type of model provide project managers with insight and confidence into the effectiveness of rocket propulsion ground testing.

Predicting risk for portal vein thrombosis in acute pancreatitis patients: A comparison of radical basis function artificial neural network and logistic regression models.

PubMed

Fei, Yang; Hu, Jian; Gao, Kun; Tu, Jianfeng; Li, Wei-Qin; Wang, Wei

2017-06-01

To construct a radical basis function (RBF) artificial neural networks (ANNs) model to predict the incidence of acute pancreatitis (AP)-induced portal vein thrombosis. The analysis included 353 patients with AP who had admitted between January 2011 and December 2015. RBF ANNs model and logistic regression model were constructed based on eleven factors relevant to AP respectively. Statistical indexes were used to evaluate the value of the prediction in two models. The predict sensitivity, specificity, positive predictive value, negative predictive value and accuracy by RBF ANNs model for PVT were 73.3%, 91.4%, 68.8%, 93.0% and 87.7%, respectively. There were significant differences between the RBF ANNs and logistic regression models in these parameters (P<0.05). In addition, a comparison of the area under receiver operating characteristic curves of the two models showed a statistically significant difference (P<0.05). The RBF ANNs model is more likely to predict the occurrence of PVT induced by AP than logistic regression model. D-dimer, AMY, Hct and PT were important prediction factors of approval for AP-induced PVT. Copyright © 2017 Elsevier Inc. All rights reserved.

Who Will Win?: Predicting the Presidential Election Using Linear Regression

ERIC Educational Resources Information Center

Lamb, John H.

2007-01-01

This article outlines a linear regression activity that engages learners, uses technology, and fosters cooperation. Students generated least-squares linear regression equations using TI-83 Plus[TM] graphing calculators, Microsoft[C] Excel, and paper-and-pencil calculations using derived normal equations to predict the 2004 presidential election.…

EXpectation Propagation LOgistic REgRession (EXPLORER): Distributed Privacy-Preserving Online Model Learning

PubMed Central

Wang, Shuang; Jiang, Xiaoqian; Wu, Yuan; Cui, Lijuan; Cheng, Samuel; Ohno-Machado, Lucila

2013-01-01

We developed an EXpectation Propagation LOgistic REgRession (EXPLORER) model for distributed privacy-preserving online learning. The proposed framework provides a high level guarantee for protecting sensitive information, since the information exchanged between the server and the client is the encrypted posterior distribution of coefficients. Through experimental results, EXPLORER shows the same performance (e.g., discrimination, calibration, feature selection etc.) as the traditional frequentist Logistic Regression model, but provides more flexibility in model updating. That is, EXPLORER can be updated one point at a time rather than having to retrain the entire data set when new observations are recorded. The proposed EXPLORER supports asynchronized communication, which relieves the participants from coordinating with one another, and prevents service breakdown from the absence of participants or interrupted communications. PMID:23562651

Using regression equations built from summary data in the psychological assessment of the individual case: extension to multiple regression.

PubMed

Crawford, John R; Garthwaite, Paul H; Denham, Annie K; Chelune, Gordon J

2012-12-01

Regression equations have many useful roles in psychological assessment. Moreover, there is a large reservoir of published data that could be used to build regression equations; these equations could then be employed to test a wide variety of hypotheses concerning the functioning of individual cases. This resource is currently underused because (a) not all psychologists are aware that regression equations can be built not only from raw data but also using only basic summary data for a sample, and (b) the computations involved are tedious and prone to error. In an attempt to overcome these barriers, Crawford and Garthwaite (2007) provided methods to build and apply simple linear regression models using summary statistics as data. In the present study, we extend this work to set out the steps required to build multiple regression models from sample summary statistics and the further steps required to compute the associated statistics for drawing inferences concerning an individual case. We also develop, describe, and make available a computer program that implements these methods. Although there are caveats associated with the use of the methods, these need to be balanced against pragmatic considerations and against the alternative of either entirely ignoring a pertinent data set or using it informally to provide a clinical "guesstimate." Upgraded versions of earlier programs for regression in the single case are also provided; these add the point and interval estimates of effect size developed in the present article.

Dietary consumption patterns and laryngeal cancer risk.

PubMed

Vlastarakos, Petros V; Vassileiou, Andrianna; Delicha, Evie; Kikidis, Dimitrios; Protopapas, Dimosthenis; Nikolopoulos, Thomas P

2016-06-01

We conducted a case-control study to investigate the effect of diet on laryngeal carcinogenesis. Our study population was made up of 140 participants-70 patients with laryngeal cancer (LC) and 70 controls with a non-neoplastic condition that was unrelated to diet, smoking, or alcohol. A food-frequency questionnaire determined the mean consumption of 113 different items during the 3 years prior to symptom onset. Total energy intake and cooking mode were also noted. The relative risk, odds ratio (OR), and 95% confidence interval (CI) were estimated by multiple logistic regression analysis. We found that the total energy intake was significantly higher in the LC group (p < 0.001), and that the difference remained statistically significant after logistic regression analysis (p < 0.001; OR: 118.70). Notably, meat consumption was higher in the LC group (p < 0.001), and the difference remained significant after logistic regression analysis (p = 0.029; OR: 1.16). LC patients also consumed significantly more fried food (p = 0.036); this difference also remained significant in the logistic regression model (p = 0.026; OR: 5.45). The LC group also consumed significantly more seafood (p = 0.012); the difference persisted after logistic regression analysis (p = 0.009; OR: 2.48), with the consumption of shrimp proving detrimental (p = 0.049; OR: 2.18). Finally, the intake of zinc was significantly higher in the LC group before and after logistic regression analysis (p = 0.034 and p = 0.011; OR: 30.15, respectively). Cereal consumption (including pastas) was also higher among the LC patients (p = 0.043), with logistic regression analysis showing that their negative effect was possibly associated with the sauces and dressings that traditionally accompany pasta dishes (p = 0.006; OR: 4.78). Conversely, a higher consumption of dairy products was found in controls (p < 0.05); logistic regression analysis showed that calcium appeared to be protective at the micronutrient level (p < 0.001; OR: 0.27). We found no difference in the overall consumption of fruits and vegetables between the LC patients and controls; however, the LC patients did have a greater consumption of cooked tomatoes and cooked root vegetables (p = 0.039 for both), and the controls had more consumption of leeks (p = 0.042) and, among controls younger than 65 years, cooked beans (p = 0.037). Lemon (p = 0.037), squeezed fruit juice (p = 0.032), and watermelon (p = 0.018) were also more frequently consumed by the controls. Other differences at the micronutrient level included greater consumption by the LC patients of retinol (p = 0.044), polyunsaturated fats (p = 0.041), and linoleic acid (p = 0.008); LC patients younger than 65 years also had greater intake of riboflavin (p = 0.045). We conclude that the differences in dietary consumption patterns between LC patients and controls indicate a possible role for lifestyle modifications involving nutritional factors as a means of decreasing the risk of laryngeal cancer.

Comparing Alternative Kernels for the Kernel Method of Test Equating: Gaussian, Logistic, and Uniform Kernels. Research Report. ETS RR-08-12

ERIC Educational Resources Information Center

Lee, Yi-Hsuan; von Davier, Alina A.

2008-01-01

The kernel equating method (von Davier, Holland, & Thayer, 2004) is based on a flexible family of equipercentile-like equating functions that use a Gaussian kernel to continuize the discrete score distributions. While the classical equipercentile, or percentile-rank, equating method carries out the continuization step by linear interpolation,…

Technique for estimating the 2- to 500-year flood discharges on unregulated streams in rural Missouri

USGS Publications Warehouse

Alexander, Terry W.; Wilson, Gary L.

1995-01-01

A generalized least-squares regression technique was used to relate the 2- to 500-year flood discharges from 278 selected streamflow-gaging stations to statistically significant basin characteristics. The regression relations (estimating equations) were defined for three hydrologic regions (I, II, and III) in rural Missouri. Ordinary least-squares regression analyses indicate that drainage area (Regions I, II, and III) and main-channel slope (Regions I and II) are the only basin characteristics needed for computing the 2- to 500-year design-flood discharges at gaged or ungaged stream locations. The resulting generalized least-squares regression equations provide a technique for estimating the 2-, 5-, 10-, 25-, 50-, 100-, and 500-year flood discharges on unregulated streams in rural Missouri. The regression equations for Regions I and II were developed from stream-flow-gaging stations with drainage areas ranging from 0.13 to 11,500 square miles and 0.13 to 14,000 square miles, and main-channel slopes ranging from 1.35 to 150 feet per mile and 1.20 to 279 feet per mile. The regression equations for Region III were developed from streamflow-gaging stations with drainage areas ranging from 0.48 to 1,040 square miles. Standard errors of estimate for the generalized least-squares regression equations in Regions I, II, and m ranged from 30 to 49 percent.

Modeling time-location patterns of inner-city high school students in New York and Los Angeles using a longitudinal approach with generalized estimating equations.

PubMed

Decastro, B Rey; Sax, Sonja N; Chillrud, Steven N; Kinney, Patrick L; Spengler, John D

2007-05-01

The TEACH Project obtained subjects' time-location information as part of its assessment of personal exposures to air toxics for high school students in two major urban areas. This report uses a longitudinal modeling approach to characterize the association between demographic and temporal predictors and the subjects' time-location behavior for three microenvironments--indoor-home, indoor-school, and outdoors. Such a longitudinal approach has not, to the knowledge of the authors, been previously applied to time-location data. Subjects were 14- to 19-year-old, self reported non-smokers, and were recruited from high schools in New York, NY (31 subjects: nine male, 22 female) and Los Angeles, CA (31 subjects: eight male, 23 female). Subjects reported their time-location in structured 24-h diaries with 15-min intervals for three consecutive weekdays in each of winter and summer-fall seasons in New York and Los Angeles during 1999-2000. The data set contained 15,009 observations. A longitudinal logistic regression model was run for each microenvironment where the binary outcome indicated the subject's presence in a microenvironment during a 15-min period. The generalized estimating equation (GEE) technique with alternating logistic regressions was used to account for the correlation of observations within each subject. The multivariate models revealed complex time-location patterns, with subjects predominantly in the indoor-home microenvironment, but also with a clear influence of the school schedule. The models also found that a subject's presence in a particular microenvironment may be significantly positively correlated for as long as 45 min before the current observation. Demographic variables were also predictive of time-location behavior: for the indoor-home microenvironment, having an after school job (OR=0.67 [95% confidence interval: 0.54:0.85]); for indoor-school, living in New York (0.42 [0.29:0.59]); and for outdoor, being 16-year-old (0.80 [0.67:0.96]), 17-year-old (0.71 [0.54:0.92]), and having an after school job (1.29 [1.07:1.56]).

Predicting Survival From Large Echocardiography and Electronic Health Record Datasets: Optimization With Machine Learning.

PubMed

Samad, Manar D; Ulloa, Alvaro; Wehner, Gregory J; Jing, Linyuan; Hartzel, Dustin; Good, Christopher W; Williams, Brent A; Haggerty, Christopher M; Fornwalt, Brandon K

2018-06-09

The goal of this study was to use machine learning to more accurately predict survival after echocardiography. Predicting patient outcomes (e.g., survival) following echocardiography is primarily based on ejection fraction (EF) and comorbidities. However, there may be significant predictive information within additional echocardiography-derived measurements combined with clinical electronic health record data. Mortality was studied in 171,510 unselected patients who underwent 331,317 echocardiograms in a large regional health system. We investigated the predictive performance of nonlinear machine learning models compared with that of linear logistic regression models using 3 different inputs: 1) clinical variables, including 90 cardiovascular-relevant International Classification of Diseases, Tenth Revision, codes, and age, sex, height, weight, heart rate, blood pressures, low-density lipoprotein, high-density lipoprotein, and smoking; 2) clinical variables plus physician-reported EF; and 3) clinical variables and EF, plus 57 additional echocardiographic measurements. Missing data were imputed with a multivariate imputation by using a chained equations algorithm (MICE). We compared models versus each other and baseline clinical scoring systems by using a mean area under the curve (AUC) over 10 cross-validation folds and across 10 survival durations (6 to 60 months). Machine learning models achieved significantly higher prediction accuracy (all AUC >0.82) over common clinical risk scores (AUC = 0.61 to 0.79), with the nonlinear random forest models outperforming logistic regression (p < 0.01). The random forest model including all echocardiographic measurements yielded the highest prediction accuracy (p < 0.01 across all models and survival durations). Only 10 variables were needed to achieve 96% of the maximum prediction accuracy, with 6 of these variables being derived from echocardiography. Tricuspid regurgitation velocity was more predictive of survival than LVEF. In a subset of studies with complete data for the top 10 variables, multivariate imputation by chained equations yielded slightly reduced predictive accuracies (difference in AUC of 0.003) compared with the original data. Machine learning can fully utilize large combinations of disparate input variables to predict survival after echocardiography with superior accuracy. Copyright © 2018 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.

Numerical solution of a logistic growth model for a population with Allee effect considering fuzzy initial values and fuzzy parameters

NASA Astrophysics Data System (ADS)

Amarti, Z.; Nurkholipah, N. S.; Anggriani, N.; Supriatna, A. K.

2018-03-01

Predicting the future of population number is among the important factors that affect the consideration in preparing a good management for the population. This has been done by various known method, one among them is by developing a mathematical model describing the growth of the population. The model usually takes form in a differential equation or a system of differential equations, depending on the complexity of the underlying properties of the population. The most widely used growth models currently are those having a sigmoid solution of time series, including the Verhulst logistic equation and the Gompertz equation. In this paper we consider the Allee effect of the Verhulst’s logistic population model. The Allee effect is a phenomenon in biology showing a high correlation between population size or density and the mean individual fitness of the population. The method used to derive the solution is the Runge-Kutta numerical scheme, since it is in general regarded as one among the good numerical scheme which is relatively easy to implement. Further exploration is done via the fuzzy theoretical approach to accommodate the impreciseness of the initial values and parameters in the model.

Estimation of peak-discharge frequency of urban streams in Jefferson County, Kentucky

USGS Publications Warehouse

Martin, Gary R.; Ruhl, Kevin J.; Moore, Brian L.; Rose, Martin F.

1997-01-01

An investigation of flood-hydrograph characteristics for streams in urban Jefferson County, Kentucky, was made to obtain hydrologic information needed for waterresources management. Equations for estimating peak-discharge frequencies for ungaged streams in the county were developed by combining (1) long-term annual peakdischarge data and rainfall-runoff data collected from 1991 to 1995 in 13 urban basins and (2) long-term annual peak-discharge data in four rural basins located in hydrologically similar areas of neighboring counties. The basins ranged in size from 1.36 to 64.0 square miles. The U.S. Geological Survey Rainfall- Runoff Model (RRM) was calibrated for each of the urban basins. The calibrated models were used with long-term, historical rainfall and pan-evaporation data to simulate 79 years of annual peak-discharge data. Peak-discharge frequencies were estimated by fitting the logarithms of the annual peak discharges to a Pearson-Type III frequency distribution. The simulated peak-discharge frequencies were adjusted for improved reliability by application of bias-correction factors derived from peakdischarge frequencies based on local, observed annual peak discharges. The three-parameter and the preferred seven-parameter nationwide urban-peak-discharge regression equations previously developed by USGS investigators provided biased (high) estimates for the urban basins studied. Generalized-least-square regression procedures were used to relate peakdischarge frequency to selected basin characteristics. Regression equations were developed to estimate peak-discharge frequency by adjusting peak-dischargefrequency estimates made by use of the threeparameter nationwide urban regression equations. The regression equations are presented in equivalent forms as functions of contributing drainage area, main-channel slope, and basin development factor, which is an index for measuring the efficiency of the basin drainage system. Estimates of peak discharges for streams in the county can be made for the 2-, 5-, 10-, 25-, 50-, and 100-year recurrence intervals by use of the regression equations. The average standard errors of prediction of the regression equations ranges from ? 34 to ? 45 percent. The regression equations are applicable to ungaged streams in the county having a specific range of basin characteristics.

Techniques for estimating flood-peak discharges of rural, unregulated streams in Ohio

USGS Publications Warehouse

Koltun, G.F.

2003-01-01

Regional equations for estimating 2-, 5-, 10-, 25-, 50-, 100-, and 500-year flood-peak discharges at ungaged sites on rural, unregulated streams in Ohio were developed by means of ordinary and generalized least-squares (GLS) regression techniques. One-variable, simple equations and three-variable, full-model equations were developed on the basis of selected basin characteristics and flood-frequency estimates determined for 305 streamflow-gaging stations in Ohio and adjacent states. The average standard errors of prediction ranged from about 39 to 49 percent for the simple equations, and from about 34 to 41 percent for the full-model equations. Flood-frequency estimates determined by means of log-Pearson Type III analyses are reported along with weighted flood-frequency estimates, computed as a function of the log-Pearson Type III estimates and the regression estimates. Values of explanatory variables used in the regression models were determined from digital spatial data sets by means of a geographic information system (GIS), with the exception of drainage area, which was determined by digitizing the area within basin boundaries manually delineated on topographic maps. Use of GIS-based explanatory variables represents a major departure in methodology from that described in previous reports on estimating flood-frequency characteristics of Ohio streams. Examples are presented illustrating application of the regression equations to ungaged sites on ungaged and gaged streams. A method is provided to adjust regression estimates for ungaged sites by use of weighted and regression estimates for a gaged site on the same stream. A region-of-influence method, which employs a computer program to estimate flood-frequency characteristics for ungaged sites based on data from gaged sites with similar characteristics, was also tested and compared to the GLS full-model equations. For all recurrence intervals, the GLS full-model equations had superior prediction accuracy relative to the simple equations and therefore are recommended for use.

The joint effects of risk status, gender, early literacy and cognitive skills on the presence of dyslexia among a group of high-risk Chinese children.

PubMed

Wong, Simpson W L; McBride-Chang, Catherine; Lam, Catherine; Chan, Becky; Lam, Fanny W F; Doo, Sylvia

2012-02-01

This study sought to examine factors that are predictive of future developmental dyslexia among a group of 5-year-old Chinese children at risk for dyslexia, including 62 children with a sibling who had been previously diagnosed with dyslexia and 52 children who manifested clinical at-risk factors in aspects of language according to testing by paediatricians. The age-5 performances on various literacy and cognitive tasks, gender and group status (familial risk or language delayed) were used to predict developmental dyslexia 2 years later using logistic regression analysis. Results showed that greater risk of dyslexia was related to slower rapid automatized naming, lower scores on morphological awareness, Chinese character recognition and English letter naming, and gender (boys had more risk). Three logistic equations were generated for estimating individual risk of dyslexia. The strongest models were those that included all print-related variables (including speeded number naming, character recognition and letter identification) and gender, with about 70% accuracy or above. Early identification of those Chinese children at risk for dyslexia can facilitate better dyslexia risk management. Copyright © 2012 John Wiley & Sons, Ltd.

A Comparison of the Logistic Regression and Contingency Table Methods for Simultaneous Detection of Uniform and Nonuniform DIF

ERIC Educational Resources Information Center

Guler, Nese; Penfield, Randall D.

2009-01-01

In this study, we investigate the logistic regression (LR), Mantel-Haenszel (MH), and Breslow-Day (BD) procedures for the simultaneous detection of both uniform and nonuniform differential item functioning (DIF). A simulation study was used to assess and compare the Type I error rate and power of a combined decision rule (CDR), which assesses DIF…

The Overall Odds Ratio as an Intuitive Effect Size Index for Multiple Logistic Regression: Examination of Further Refinements

ERIC Educational Resources Information Center

Le, Huy; Marcus, Justin

2012-01-01

This study used Monte Carlo simulation to examine the properties of the overall odds ratio (OOR), which was recently introduced as an index for overall effect size in multiple logistic regression. It was found that the OOR was relatively independent of study base rate and performed better than most commonly used R-square analogs in indexing model…

Predicting Student Success on the Texas Chemistry STAAR Test: A Logistic Regression Analysis

ERIC Educational Resources Information Center

Johnson, William L.; Johnson, Annabel M.; Johnson, Jared

2012-01-01

Background: The context is the new Texas STAAR end-of-course testing program. Purpose: The authors developed a logistic regression model to predict who would pass-or-fail the new Texas chemistry STAAR end-of-course exam. Setting: Robert E. Lee High School (5A) with an enrollment of 2700 students, Tyler, Texas. Date of the study was the 2011-2012…

Using ROC curves to compare neural networks and logistic regression for modeling individual noncatastrophic tree mortality

Treesearch

Susan L. King

2003-01-01

The performance of two classifiers, logistic regression and neural networks, are compared for modeling noncatastrophic individual tree mortality for 21 species of trees in West Virginia. The output of the classifier is usually a continuous number between 0 and 1. A threshold is selected between 0 and 1 and all of the trees below the threshold are classified as...

Logistic regression trees for initial selection of interesting loci in case-control studies

PubMed Central

Nickolov, Radoslav Z; Milanov, Valentin B

2007-01-01

Modern genetic epidemiology faces the challenge of dealing with hundreds of thousands of genetic markers. The selection of a small initial subset of interesting markers for further investigation can greatly facilitate genetic studies. In this contribution we suggest the use of a logistic regression tree algorithm known as logistic tree with unbiased selection. Using the simulated data provided for Genetic Analysis Workshop 15, we show how this algorithm, with incorporation of multifactor dimensionality reduction method, can reduce an initial large pool of markers to a small set that includes the interesting markers with high probability. PMID:18466557

Using Logistic Regression to Predict the Probability of Debris Flows in Areas Burned by Wildfires, Southern California, 2003-2006

USGS Publications Warehouse

Rupert, Michael G.; Cannon, Susan H.; Gartner, Joseph E.; Michael, John A.; Helsel, Dennis R.

2008-01-01

Logistic regression was used to develop statistical models that can be used to predict the probability of debris flows in areas recently burned by wildfires by using data from 14 wildfires that burned in southern California during 2003-2006. Twenty-eight independent variables describing the basin morphology, burn severity, rainfall, and soil properties of 306 drainage basins located within those burned areas were evaluated. The models were developed as follows: (1) Basins that did and did not produce debris flows soon after the 2003 to 2006 fires were delineated from data in the National Elevation Dataset using a geographic information system; (2) Data describing the basin morphology, burn severity, rainfall, and soil properties were compiled for each basin. These data were then input to a statistics software package for analysis using logistic regression; and (3) Relations between the occurrence or absence of debris flows and the basin morphology, burn severity, rainfall, and soil properties were evaluated, and five multivariate logistic regression models were constructed. All possible combinations of independent variables were evaluated to determine which combinations produced the most effective models, and the multivariate models that best predicted the occurrence of debris flows were identified. Percentage of high burn severity and 3-hour peak rainfall intensity were significant variables in all models. Soil organic matter content and soil clay content were significant variables in all models except Model 5. Soil slope was a significant variable in all models except Model 4. The most suitable model can be selected from these five models on the basis of the availability of independent variables in the particular area of interest and field checking of probability maps. The multivariate logistic regression models can be entered into a geographic information system, and maps showing the probability of debris flows can be constructed in recently burned areas of southern California. This study demonstrates that logistic regression is a valuable tool for developing models that predict the probability of debris flows occurring in recently burned landscapes.

Polymorphism Thr160Thr in SRD5A1, involved in the progesterone metabolism, modifies postmenopausal breast cancer risk associated with menopausal hormone therapy.

PubMed

Hein, R; Abbas, S; Seibold, P; Salazar, R; Flesch-Janys, D; Chang-Claude, J

2012-01-01

Menopausal hormone therapy (MHT) is associated with an increased breast cancer risk in postmenopausal women, with combined estrogen-progestagen therapy posing a greater risk than estrogen monotherapy. However, few studies focused on potential effect modification of MHT-associated breast cancer risk by genetic polymorphisms in the progesterone metabolism. We assessed effect modification of MHT use by five coding single nucleotide polymorphisms (SNPs) in the progesterone metabolizing enzymes AKR1C3 (rs7741), AKR1C4 (rs3829125, rs17134592), and SRD5A1 (rs248793, rs3736316) using a two-center population-based case-control study from Germany with 2,502 postmenopausal breast cancer patients and 4,833 matched controls. An empirical-Bayes procedure that tests for interaction using a weighted combination of the prospective and the retrospective case-control estimators as well as standard prospective logistic regression were applied to assess multiplicative statistical interaction between polymorphisms and duration of MHT use with regard to breast cancer risk assuming a log-additive mode of inheritance. No genetic marginal effects were observed. Breast cancer risk associated with duration of combined therapy was significantly modified by SRD5A1_rs3736316, showing a reduced risk elevation in carriers of the minor allele (p (interaction,empirical-Bayes) = 0.006 using the empirical-Bayes method, p (interaction,logistic regression) = 0.013 using logistic regression). The risk associated with duration of use of monotherapy was increased by AKR1C3_rs7741 in minor allele carriers (p (interaction,empirical-Bayes) = 0.083, p (interaction,logistic regression) = 0.029) and decreased in minor allele carriers of two SNPs in AKR1C4 (rs3829125: p (interaction,empirical-Bayes) = 0.07, p (interaction,logistic regression) = 0.021; rs17134592: p (interaction,empirical-Bayes) = 0.101, p (interaction,logistic regression) = 0.038). After Bonferroni correction for multiple testing only SRD5A1_rs3736316 assessed using the empirical-Bayes method remained significant. Postmenopausal breast cancer risk associated with combined therapy may be modified by genetic variation in SRD5A1. Further well-powered studies are, however, required to replicate our finding.

Flood-Frequency Estimates for Streams on Kaua`i, O`ahu, Moloka`i, Maui, and Hawai`i, State of Hawai`i

USGS Publications Warehouse

Oki, Delwyn S.; Rosa, Sarah N.; Yeung, Chiu W.

2010-01-01

This study provides an updated analysis of the magnitude and frequency of peak stream discharges in Hawai`i. Annual peak-discharge data collected by the U.S. Geological Survey during and before water year 2008 (ending September 30, 2008) at stream-gaging stations were analyzed. The existing generalized-skew value for the State of Hawai`i was retained, although three methods were used to evaluate whether an update was needed. Regional regression equations were developed for peak discharges with 2-, 5-, 10-, 25-, 50-, 100-, and 500-year recurrence intervals for unregulated streams (those for which peak discharges are not affected to a large extent by upstream reservoirs, dams, diversions, or other structures) in areas with less than 20 percent combined medium- and high-intensity development on Kaua`i, O`ahu, Moloka`i, Maui, and Hawai`i. The generalized-least-squares (GLS) regression equations relate peak stream discharge to quantified basin characteristics (for example, drainage-basin area and mean annual rainfall) that were determined using geographic information system (GIS) methods. Each of the islands of Kaua`i,O`ahu, Moloka`i, Maui, and Hawai`i was divided into two regions, generally corresponding to a wet region and a dry region. Unique peak-discharge regression equations were developed for each region. The regression equations developed for this study have standard errors of prediction ranging from 16 to 620 percent. Standard errors of prediction are greatest for regression equations developed for leeward Moloka`i and southern Hawai`i. In general, estimated 100-year peak discharges from this study are lower than those from previous studies, which may reflect the longer periods of record used in this study. Each regression equation is valid within the range of values of the explanatory variables used to develop the equation. The regression equations were developed using peak-discharge data from streams that are mainly unregulated, and they should not be used to estimate peak discharges in regulated streams. Use of a regression equation beyond its limits will produce peak-discharge estimates with unknown error and should therefore be avoided. Improved estimates of the magnitude and frequency of peak discharges in Hawai`i will require continued operation of existing stream-gaging stations and operation of additional gaging stations for areas such as Moloka`i and Hawai`i, where limited stream-gaging data are available.

Breastfeeding Reduces Childhood Obesity Risks.

PubMed

Wang, Liang; Collins, Candice; Ratliff, Melanie; Xie, Bin; Wang, Youfa

2017-06-01

The present study examined the effects of breastfeeding and its duration on the development of childhood obesity from 24 months through grade 6. U.S. longitudinal data collected from 1234 children were analyzed using logistic regression models and generalized estimating equation (GEE). Child height and weight were measured six times at ages of 24 months, 36 months, 54 months, grade 1, grade 3, and grade 6. During the early 1990s, prevalence of breastfeeding was low in the United States, 60% and 48% at 1 and 6 months, respectively. Nonsmoking, white, married mothers with both parents in the household, and with income above the poverty line, were more likely to breastfeed at 1 month of age of their babies. Obesity rate of the children increased with age from 24 months to grade 6. Logistic regression showed that breastfeeding at month 1 was associated with 53% (odds ratio [OR]: 0.47, 95% confidence interval [CI]: 0.30-0.73) and 47% (OR: 0.53, 95% CI: 0.36-0.78) decreased risks for childhood obesity at grades 1 and 6, respectively. GEE analysis showed that breastfeeding at 1 month reduced risk for childhood obesity by 36% (95% CI: 0.47-0.88) from ages 24 months through grade 6. Regarding breastfeeding duration, more than 6 months (vs. never) was associated with a decreased risk for childhood obesity by 42% (OR: 0.58, 95% CI: 0.36-0.94). Breastfeeding at 1 month and more than 6 months reduced the risk of childhood obesity. Rate of breastfeeding was low in the United States in the 1990s, which may have had long-term implications on children.

Estimation of Ordinary Differential Equation Parameters Using Constrained Local Polynomial Regression.

PubMed

Ding, A Adam; Wu, Hulin

2014-10-01

We propose a new method to use a constrained local polynomial regression to estimate the unknown parameters in ordinary differential equation models with a goal of improving the smoothing-based two-stage pseudo-least squares estimate. The equation constraints are derived from the differential equation model and are incorporated into the local polynomial regression in order to estimate the unknown parameters in the differential equation model. We also derive the asymptotic bias and variance of the proposed estimator. Our simulation studies show that our new estimator is clearly better than the pseudo-least squares estimator in estimation accuracy with a small price of computational cost. An application example on immune cell kinetics and trafficking for influenza infection further illustrates the benefits of the proposed new method.

Estimation of Ordinary Differential Equation Parameters Using Constrained Local Polynomial Regression

PubMed Central

Ding, A. Adam; Wu, Hulin

2015-01-01

We propose a new method to use a constrained local polynomial regression to estimate the unknown parameters in ordinary differential equation models with a goal of improving the smoothing-based two-stage pseudo-least squares estimate. The equation constraints are derived from the differential equation model and are incorporated into the local polynomial regression in order to estimate the unknown parameters in the differential equation model. We also derive the asymptotic bias and variance of the proposed estimator. Our simulation studies show that our new estimator is clearly better than the pseudo-least squares estimator in estimation accuracy with a small price of computational cost. An application example on immune cell kinetics and trafficking for influenza infection further illustrates the benefits of the proposed new method. PMID:26401093

A method for the selection of a functional form for a thermodynamic equation of state using weighted linear least squares stepwise regression

NASA Technical Reports Server (NTRS)

Jacobsen, R. T.; Stewart, R. B.; Crain, R. W., Jr.; Rose, G. L.; Myers, A. F.

1976-01-01

A method was developed for establishing a rational choice of the terms to be included in an equation of state with a large number of adjustable coefficients. The methods presented were developed for use in the determination of an equation of state for oxygen and nitrogen. However, a general application of the methods is possible in studies involving the determination of an optimum polynomial equation for fitting a large number of data points. The data considered in the least squares problem are experimental thermodynamic pressure-density-temperature data. Attention is given to a description of stepwise multiple regression and the use of stepwise regression in the determination of an equation of state for oxygen and nitrogen.

Applications of statistics to medical science, III. Correlation and regression.

PubMed

Watanabe, Hiroshi

2012-01-01

In this third part of a series surveying medical statistics, the concepts of correlation and regression are reviewed. In particular, methods of linear regression and logistic regression are discussed. Arguments related to survival analysis will be made in a subsequent paper.

Density-dependence as a size-independent regulatory mechanism.

PubMed

de Vladar, Harold P

2006-01-21

The growth function of populations is central in biomathematics. The main dogma is the existence of density-dependence mechanisms, which can be modelled with distinct functional forms that depend on the size of the population. One important class of regulatory functions is the theta-logistic, which generalizes the logistic equation. Using this model as a motivation, this paper introduces a simple dynamical reformulation that generalizes many growth functions. The reformulation consists of two equations, one for population size, and one for the growth rate. Furthermore, the model shows that although population is density-dependent, the dynamics of the growth rate does not depend either on population size, nor on the carrying capacity. Actually, the growth equation is uncoupled from the population size equation, and the model has only two parameters, a Malthusian parameter rho and a competition coefficient theta. Distinct sign combinations of these parameters reproduce not only the family of theta-logistics, but also the van Bertalanffy, Gompertz and Potential Growth equations, among other possibilities. It is also shown that, except for two critical points, there is a general size-scaling relation that includes those appearing in the most important allometric theories, including the recently proposed Metabolic Theory of Ecology. With this model, several issues of general interest are discussed such as the growth of animal population, extinctions, cell growth and allometry, and the effect of environment over a population.

Computing group cardinality constraint solutions for logistic regression problems.

PubMed

Zhang, Yong; Kwon, Dongjin; Pohl, Kilian M

2017-01-01

We derive an algorithm to directly solve logistic regression based on cardinality constraint, group sparsity and use it to classify intra-subject MRI sequences (e.g. cine MRIs) of healthy from diseased subjects. Group cardinality constraint models are often applied to medical images in order to avoid overfitting of the classifier to the training data. Solutions within these models are generally determined by relaxing the cardinality constraint to a weighted feature selection scheme. However, these solutions relate to the original sparse problem only under specific assumptions, which generally do not hold for medical image applications. In addition, inferring clinical meaning from features weighted by a classifier is an ongoing topic of discussion. Avoiding weighing features, we propose to directly solve the group cardinality constraint logistic regression problem by generalizing the Penalty Decomposition method. To do so, we assume that an intra-subject series of images represents repeated samples of the same disease patterns. We model this assumption by combining series of measurements created by a feature across time into a single group. Our algorithm then derives a solution within that model by decoupling the minimization of the logistic regression function from enforcing the group sparsity constraint. The minimum to the smooth and convex logistic regression problem is determined via gradient descent while we derive a closed form solution for finding a sparse approximation of that minimum. We apply our method to cine MRI of 38 healthy controls and 44 adult patients that received reconstructive surgery of Tetralogy of Fallot (TOF) during infancy. Our method correctly identifies regions impacted by TOF and generally obtains statistically significant higher classification accuracy than alternative solutions to this model, i.e., ones relaxing group cardinality constraints. Copyright © 2016 Elsevier B.V. All rights reserved.

Influential factors of red-light running at signalized intersection and prediction using a rare events logistic regression model.

PubMed

Ren, Yilong; Wang, Yunpeng; Wu, Xinkai; Yu, Guizhen; Ding, Chuan

2016-10-01

Red light running (RLR) has become a major safety concern at signalized intersection. To prevent RLR related crashes, it is critical to identify the factors that significantly impact the drivers' behaviors of RLR, and to predict potential RLR in real time. In this research, 9-month's RLR events extracted from high-resolution traffic data collected by loop detectors from three signalized intersections were applied to identify the factors that significantly affect RLR behaviors. The data analysis indicated that occupancy time, time gap, used yellow time, time left to yellow start, whether the preceding vehicle runs through the intersection during yellow, and whether there is a vehicle passing through the intersection on the adjacent lane were significantly factors for RLR behaviors. Furthermore, due to the rare events nature of RLR, a modified rare events logistic regression model was developed for RLR prediction. The rare events logistic regression method has been applied in many fields for rare events studies and shows impressive performance, but so far none of previous research has applied this method to study RLR. The results showed that the rare events logistic regression model performed significantly better than the standard logistic regression model. More importantly, the proposed RLR prediction method is purely based on loop detector data collected from a single advance loop detector located 400 feet away from stop-bar. This brings great potential for future field applications of the proposed method since loops have been widely implemented in many intersections and can collect data in real time. This research is expected to contribute to the improvement of intersection safety significantly. Copyright © 2016 Elsevier Ltd. All rights reserved.

Use of genetic programming, logistic regression, and artificial neural nets to predict readmission after coronary artery bypass surgery.

PubMed

Engoren, Milo; Habib, Robert H; Dooner, John J; Schwann, Thomas A

2013-08-01

As many as 14 % of patients undergoing coronary artery bypass surgery are readmitted within 30 days. Readmission is usually the result of morbidity and may lead to death. The purpose of this study is to develop and compare statistical and genetic programming models to predict readmission. Patients were divided into separate Construction and Validation populations. Using 88 variables, logistic regression, genetic programs, and artificial neural nets were used to develop predictive models. Models were first constructed and tested on the Construction populations, then validated on the Validation population. Areas under the receiver operator characteristic curves (AU ROC) were used to compare the models. Two hundred and two patients (7.6 %) in the 2,644 patient Construction group and 216 (8.0 %) of the 2,711 patient Validation group were re-admitted within 30 days of CABG surgery. Logistic regression predicted readmission with AU ROC = .675 ± .021 in the Construction group. Genetic programs significantly improved the accuracy, AU ROC = .767 ± .001, p < .001). Artificial neural nets were less accurate with AU ROC = 0.597 ± .001 in the Construction group. Predictive accuracy of all three techniques fell in the Validation group. However, the accuracy of genetic programming (AU ROC = .654 ± .001) was still trivially but statistically non-significantly better than that of the logistic regression (AU ROC = .644 ± .020, p = .61). Genetic programming and logistic regression provide alternative methods to predict readmission that are similarly accurate.

Artificial neural network, genetic algorithm, and logistic regression applications for predicting renal colic in emergency settings.

PubMed

Eken, Cenker; Bilge, Ugur; Kartal, Mutlu; Eray, Oktay

2009-06-03

Logistic regression is the most common statistical model for processing multivariate data in the medical literature. Artificial intelligence models like an artificial neural network (ANN) and genetic algorithm (GA) may also be useful to interpret medical data. The purpose of this study was to perform artificial intelligence models on a medical data sheet and compare to logistic regression. ANN, GA, and logistic regression analysis were carried out on a data sheet of a previously published article regarding patients presenting to an emergency department with flank pain suspicious for renal colic. The study population was composed of 227 patients: 176 patients had a diagnosis of urinary stone, while 51 ultimately had no calculus. The GA found two decision rules in predicting urinary stones. Rule 1 consisted of being male, pain not spreading to back, and no fever. In rule 2, pelvicaliceal dilatation on bedside ultrasonography replaced no fever. ANN, GA rule 1, GA rule 2, and logistic regression had a sensitivity of 94.9, 67.6, 56.8, and 95.5%, a specificity of 78.4, 76.47, 86.3, and 47.1%, a positive likelihood ratio of 4.4, 2.9, 4.1, and 1.8, and a negative likelihood ratio of 0.06, 0.42, 0.5, and 0.09, respectively. The area under the curve was found to be 0.867, 0.720, 0.715, and 0.713 for all applications, respectively. Data mining techniques such as ANN and GA can be used for predicting renal colic in emergency settings and to constitute clinical decision rules. They may be an alternative to conventional multivariate analysis applications used in biostatistics.

Methods for estimating selected low-flow frequency statistics and mean annual flow for ungaged locations on streams in North Georgia

USGS Publications Warehouse

Gotvald, Anthony J.

2017-01-13

The U.S. Geological Survey, in cooperation with the Georgia Department of Natural Resources, Environmental Protection Division, developed regional regression equations for estimating selected low-flow frequency and mean annual flow statistics for ungaged streams in north Georgia that are not substantially affected by regulation, diversions, or urbanization. Selected low-flow frequency statistics and basin characteristics for 56 streamgage locations within north Georgia and 75 miles beyond the State’s borders in Alabama, Tennessee, North Carolina, and South Carolina were combined to form the final dataset used in the regional regression analysis. Because some of the streamgages in the study recorded zero flow, the final regression equations were developed using weighted left-censored regression analysis to analyze the flow data in an unbiased manner, with weights based on the number of years of record. The set of equations includes the annual minimum 1- and 7-day average streamflow with the 10-year recurrence interval (referred to as 1Q10 and 7Q10), monthly 7Q10, and mean annual flow. The final regional regression equations are functions of drainage area, mean annual precipitation, and relief ratio for the selected low-flow frequency statistics and drainage area and mean annual precipitation for mean annual flow. The average standard error of estimate was 13.7 percent for the mean annual flow regression equation and ranged from 26.1 to 91.6 percent for the selected low-flow frequency equations.The equations, which are based on data from streams with little to no flow alterations, can be used to provide estimates of the natural flows for selected ungaged stream locations in the area of Georgia north of the Fall Line. The regression equations are not to be used to estimate flows for streams that have been altered by the effects of major dams, surface-water withdrawals, groundwater withdrawals (pumping wells), diversions, or wastewater discharges. The regression equations should be used only for ungaged sites with drainage areas between 1.67 and 576 square miles, mean annual precipitation between 47.6 and 81.6 inches, and relief ratios between 0.146 and 0.607; these are the ranges of the explanatory variables used to develop the equations. An attempt was made to develop regional regression equations for the area of Georgia south of the Fall Line by using the same approach used during this study for north Georgia; however, the equations resulted with high average standard errors of estimates and poorly predicted flows below 0.5 cubic foot per second, which may be attributed to the karst topography common in that area.The final regression equations developed from this study are planned to be incorporated into the U.S. Geological Survey StreamStats program. StreamStats is a Web-based geographic information system that provides users with access to an assortment of analytical tools useful for water-resources planning and management, and for engineering design applications, such as the design of bridges. The StreamStats program provides streamflow statistics and basin characteristics for U.S. Geological Survey streamgage locations and ungaged sites of interest. StreamStats also can compute basin characteristics and provide estimates of streamflow statistics for ungaged sites when users select the location of a site along any stream in Georgia.

New robust statistical procedures for the polytomous logistic regression models.

PubMed

Castilla, Elena; Ghosh, Abhik; Martin, Nirian; Pardo, Leandro

2018-05-17

This article derives a new family of estimators, namely the minimum density power divergence estimators, as a robust generalization of the maximum likelihood estimator for the polytomous logistic regression model. Based on these estimators, a family of Wald-type test statistics for linear hypotheses is introduced. Robustness properties of both the proposed estimators and the test statistics are theoretically studied through the classical influence function analysis. Appropriate real life examples are presented to justify the requirement of suitable robust statistical procedures in place of the likelihood based inference for the polytomous logistic regression model. The validity of the theoretical results established in the article are further confirmed empirically through suitable simulation studies. Finally, an approach for the data-driven selection of the robustness tuning parameter is proposed with empirical justifications. © 2018, The International Biometric Society.

Nowcasting of Low-Visibility Procedure States with Ordered Logistic Regression at Vienna International Airport

NASA Astrophysics Data System (ADS)

Kneringer, Philipp; Dietz, Sebastian; Mayr, Georg J.; Zeileis, Achim

2017-04-01

Low-visibility conditions have a large impact on aviation safety and economic efficiency of airports and airlines. To support decision makers, we develop a statistical probabilistic nowcasting tool for the occurrence of capacity-reducing operations related to low visibility. The probabilities of four different low visibility classes are predicted with an ordered logistic regression model based on time series of meteorological point measurements. Potential predictor variables for the statistical models are visibility, humidity, temperature and wind measurements at several measurement sites. A stepwise variable selection method indicates that visibility and humidity measurements are the most important model inputs. The forecasts are tested with a 30 minute forecast interval up to two hours, which is a sufficient time span for tactical planning at Vienna Airport. The ordered logistic regression models outperform persistence and are competitive with human forecasters.

EXpectation Propagation LOgistic REgRession (EXPLORER): distributed privacy-preserving online model learning.

PubMed

Wang, Shuang; Jiang, Xiaoqian; Wu, Yuan; Cui, Lijuan; Cheng, Samuel; Ohno-Machado, Lucila

2013-06-01

We developed an EXpectation Propagation LOgistic REgRession (EXPLORER) model for distributed privacy-preserving online learning. The proposed framework provides a high level guarantee for protecting sensitive information, since the information exchanged between the server and the client is the encrypted posterior distribution of coefficients. Through experimental results, EXPLORER shows the same performance (e.g., discrimination, calibration, feature selection, etc.) as the traditional frequentist logistic regression model, but provides more flexibility in model updating. That is, EXPLORER can be updated one point at a time rather than having to retrain the entire data set when new observations are recorded. The proposed EXPLORER supports asynchronized communication, which relieves the participants from coordinating with one another, and prevents service breakdown from the absence of participants or interrupted communications. Copyright © 2013 Elsevier Inc. All rights reserved.

A computational approach to compare regression modelling strategies in prediction research.

PubMed

Pajouheshnia, Romin; Pestman, Wiebe R; Teerenstra, Steven; Groenwold, Rolf H H

2016-08-25

It is often unclear which approach to fit, assess and adjust a model will yield the most accurate prediction model. We present an extension of an approach for comparing modelling strategies in linear regression to the setting of logistic regression and demonstrate its application in clinical prediction research. A framework for comparing logistic regression modelling strategies by their likelihoods was formulated using a wrapper approach. Five different strategies for modelling, including simple shrinkage methods, were compared in four empirical data sets to illustrate the concept of a priori strategy comparison. Simulations were performed in both randomly generated data and empirical data to investigate the influence of data characteristics on strategy performance. We applied the comparison framework in a case study setting. Optimal strategies were selected based on the results of a priori comparisons in a clinical data set and the performance of models built according to each strategy was assessed using the Brier score and calibration plots. The performance of modelling strategies was highly dependent on the characteristics of the development data in both linear and logistic regression settings. A priori comparisons in four empirical data sets found that no strategy consistently outperformed the others. The percentage of times that a model adjustment strategy outperformed a logistic model ranged from 3.9 to 94.9 %, depending on the strategy and data set. However, in our case study setting the a priori selection of optimal methods did not result in detectable improvement in model performance when assessed in an external data set. The performance of prediction modelling strategies is a data-dependent process and can be highly variable between data sets within the same clinical domain. A priori strategy comparison can be used to determine an optimal logistic regression modelling strategy for a given data set before selecting a final modelling approach.

Cytopathologic differential diagnosis of low-grade urothelial carcinoma and reactive urothelial proliferation in bladder washings: a logistic regression analysis.

PubMed

Cakir, Ebru; Kucuk, Ulku; Pala, Emel Ebru; Sezer, Ozlem; Ekin, Rahmi Gokhan; Cakmak, Ozgur

2017-05-01

Conventional cytomorphologic assessment is the first step to establish an accurate diagnosis in urinary cytology. In cytologic preparations, the separation of low-grade urothelial carcinoma (LGUC) from reactive urothelial proliferation (RUP) can be exceedingly difficult. The bladder washing cytologies of 32 LGUC and 29 RUP were reviewed. The cytologic slides were examined for the presence or absence of the 28 cytologic features. The cytologic criteria showing statistical significance in LGUC were increased numbers of monotonous single (non-umbrella) cells, three-dimensional cellular papillary clusters without fibrovascular cores, irregular bordered clusters, atypical single cells, irregular nuclear overlap, cytoplasmic homogeneity, increased N/C ratio, pleomorphism, nuclear border irregularity, nuclear eccentricity, elongated nuclei, and hyperchromasia (p ˂ 0.05), and the cytologic criteria showing statistical significance in RUP were inflammatory background, mixture of small and large urothelial cells, loose monolayer aggregates, and vacuolated cytoplasm (p ˂ 0.05). When these variables were subjected to a stepwise logistic regression analysis, four features were selected to distinguish LGUC from RUP: increased numbers of monotonous single (non-umbrella) cells, increased nuclear cytoplasmic ratio, hyperchromasia, and presence of small and large urothelial cells (p = 0.0001). By this logistic model of the 32 cases with proven LGUC, the stepwise logistic regression analysis correctly predicted 31 (96.9%) patients with this diagnosis, and of the 29 patients with RUP, the logistic model correctly predicted 26 (89.7%) patients as having this disease. There are several cytologic features to separate LGUC from RUP. Stepwise logistic regression analysis is a valuable tool for determining the most useful cytologic criteria to distinguish these entities. © 2017 APMIS. Published by John Wiley & Sons Ltd.

Subtypes of attention deficit-hyperactivity disorder (ADHD) and cannabis use.

PubMed

Loflin, Mallory; Earleywine, Mitch; De Leo, Joseph; Hobkirk, Andrea

2014-03-01

The current study examined the association between subtypes of attention-deficit/hyperactivity disorder (ADHD) and cannabis use within a sample of 2811 current users. Data were collected in 2012 from a national U.S. survey of cannabis users. A series of logistic regression equations and chi-squares were assessed for proportional differences between users. When asked about the ADHD symptoms they have experienced when not using cannabis, a higher proportion of daily users met symptom criteria for an ADHD diagnoses of the subtypes that include hyperactive-impulsive symptoms than the inattentive subtype. For nondaily users, the proportions of users meeting symptom criteria did not differ by subtype. These results have implications for identifying which individuals with ADHD might be more likely to self-medicate using cannabis. Furthermore, these findings indirectly support research linking relevant cannabinoid receptors to regulatory control.

Attention Deficit Hyperactivity Disorder, Aggression, and Illicit Stimulant Use: Is This Self-Medication?

PubMed

Odell, Annie P; Reynolds, Grace L; Fisher, Dennis G; Huckabay, Loucine M; Pedersen, William C; Xandre, Pamela; Miočević, Milica

2017-05-01

This study compares adults with and without attention deficit hyperactivity disorder (ADHD) on measures of direct and displaced aggression and illicit drug use. Three hundred ninety-six adults were administered the Wender Utah Rating Scale, the Risk Behavior Assessment, the Aggression Questionnaire (AQ), and the Displaced Aggression Questionnaire (DAQ). Those with ADHD were higher on all scales of the AQ and DAQ, were younger at first use of amphetamines, and were more likely to have ever used crack and amphetamines. A Structural Equation Model found a significant interaction in that for those with medium and high levels of verbal aggression, ADHD predicts crack and amphetamine. Follow-up logistic regression models suggest that blacks self-medicate with crack and whites and Hispanics self-medicate with amphetamine when they have ADHD and verbal aggression.

Minute ventilation of cyclists, car and bus passengers: an experimental study.

PubMed

Zuurbier, Moniek; Hoek, Gerard; van den Hazel, Peter; Brunekreef, Bert

2009-10-27

Differences in minute ventilation between cyclists, pedestrians and other commuters influence inhaled doses of air pollution. This study estimates minute ventilation of cyclists, car and bus passengers, as part of a study on health effects of commuters' exposure to air pollutants. Thirty-four participants performed a submaximal test on a bicycle ergometer, during which heart rate and minute ventilation were measured simultaneously at increasing cycling intensity. Individual regression equations were calculated between heart rate and the natural log of minute ventilation. Heart rates were recorded during 280 two hour trips by bicycle, bus and car and were calculated into minute ventilation levels using the individual regression coefficients. Minute ventilation during bicycle rides were on average 2.1 times higher than in the car (individual range from 1.3 to 5.3) and 2.0 times higher than in the bus (individual range from 1.3 to 5.1). The ratio of minute ventilation of cycling compared to travelling by bus or car was higher in women than in men. Substantial differences in regression equations were found between individuals. The use of individual regression equations instead of average regression equations resulted in substantially better predictions of individual minute ventilations. The comparability of the gender-specific overall regression equations linking heart rate and minute ventilation with one previous American study, supports that for studies on the group level overall equations can be used. For estimating individual doses, the use of individual regression coefficients provides more precise data. Minute ventilation levels of cyclists are on average two times higher than of bus and car passengers, consistent with the ratio found in one small previous study of young adults. The study illustrates the importance of inclusion of minute ventilation data in comparing air pollution doses between different modes of transport.

Computational tools for fitting the Hill equation to dose-response curves.

PubMed

Gadagkar, Sudhindra R; Call, Gerald B

2015-01-01

Many biological response curves commonly assume a sigmoidal shape that can be approximated well by means of the 4-parameter nonlinear logistic equation, also called the Hill equation. However, estimation of the Hill equation parameters requires access to commercial software or the ability to write computer code. Here we present two user-friendly and freely available computer programs to fit the Hill equation - a Solver-based Microsoft Excel template and a stand-alone GUI-based "point and click" program, called HEPB. Both computer programs use the iterative method to estimate two of the Hill equation parameters (EC50 and the Hill slope), while constraining the values of the other two parameters (the minimum and maximum asymptotes of the response variable) to fit the Hill equation to the data. In addition, HEPB draws the prediction band at a user-defined confidence level, and determines the EC50 value for each of the limits of this band to give boundary values that help objectively delineate sensitive, normal and resistant responses to the drug being tested. Both programs were tested by analyzing twelve datasets that varied widely in data values, sample size and slope, and were found to yield estimates of the Hill equation parameters that were essentially identical to those provided by commercial software such as GraphPad Prism and nls, the statistical package in the programming language R. The Excel template provides a means to estimate the parameters of the Hill equation and plot the regression line in a familiar Microsoft Office environment. HEPB, in addition to providing the above results, also computes the prediction band for the data at a user-defined level of confidence, and determines objective cut-off values to distinguish among response types (sensitive, normal and resistant). Both programs are found to yield estimated values that are essentially the same as those from standard software such as GraphPad Prism and the R-based nls. Furthermore, HEPB also has the option to simulate 500 response values based on the range of values of the dose variable in the original data and the fit of the Hill equation to that data. Copyright © 2014. Published by Elsevier Inc.

Science of Test Research Consortium: Year Two Final Report

DTIC Science & Technology

2012-10-02

July 2012. Analysis of an Intervention for Small Unmanned Aerial System ( SUAS ) Accidents, submitted to Quality Engineering, LQEN-2012-0056. Stone... Systems Engineering. Wolf, S. E., R. R. Hill, and J. J. Pignatiello. June 2012. Using Neural Networks and Logistic Regression to Model Small Unmanned ...Human Retina. 6. Wolf, S. E. March 2012. Modeling Small Unmanned Aerial System Mishaps using Logistic Regression and Artificial Neural Networks. 7

Binary Logistic Regression Analysis for Detecting Differential Item Functioning: Effectiveness of R[superscript 2] and Delta Log Odds Ratio Effect Size Measures

ERIC Educational Resources Information Center

Hidalgo, Mª Dolores; Gómez-Benito, Juana; Zumbo, Bruno D.

2014-01-01

The authors analyze the effectiveness of the R[superscript 2] and delta log odds ratio effect size measures when using logistic regression analysis to detect differential item functioning (DIF) in dichotomous items. A simulation study was carried out, and the Type I error rate and power estimates under conditions in which only statistical testing…

Logistic quantile regression provides improved estimates for bounded avian counts: a case study of California Spotted Owl fledgling production

Treesearch

Brian S. Cade; Barry R. Noon; Rick D. Scherer; John J. Keane

2017-01-01

Counts of avian fledglings, nestlings, or clutch size that are bounded below by zero and above by some small integer form a discrete random variable distribution that is not approximated well by conventional parametric count distributions such as the Poisson or negative binomial. We developed a logistic quantile regression model to provide estimates of the empirical...

Comparison of four methods for deriving hospital standardised mortality ratios from a single hierarchical logistic regression model.

PubMed

Mohammed, Mohammed A; Manktelow, Bradley N; Hofer, Timothy P

2016-04-01

There is interest in deriving case-mix adjusted standardised mortality ratios so that comparisons between healthcare providers, such as hospitals, can be undertaken in the controversial belief that variability in standardised mortality ratios reflects quality of care. Typically standardised mortality ratios are derived using a fixed effects logistic regression model, without a hospital term in the model. This fails to account for the hierarchical structure of the data - patients nested within hospitals - and so a hierarchical logistic regression model is more appropriate. However, four methods have been advocated for deriving standardised mortality ratios from a hierarchical logistic regression model, but their agreement is not known and neither do we know which is to be preferred. We found significant differences between the four types of standardised mortality ratios because they reflect a range of underlying conceptual issues. The most subtle issue is the distinction between asking how an average patient fares in different hospitals versus how patients at a given hospital fare at an average hospital. Since the answers to these questions are not the same and since the choice between these two approaches is not obvious, the extent to which profiling hospitals on mortality can be undertaken safely and reliably, without resolving these methodological issues, remains questionable. © The Author(s) 2012.

Three methods to construct predictive models using logistic regression and likelihood ratios to facilitate adjustment for pretest probability give similar results.

PubMed

Chan, Siew Foong; Deeks, Jonathan J; Macaskill, Petra; Irwig, Les

2008-01-01

To compare three predictive models based on logistic regression to estimate adjusted likelihood ratios allowing for interdependency between diagnostic variables (tests). This study was a review of the theoretical basis, assumptions, and limitations of published models; and a statistical extension of methods and application to a case study of the diagnosis of obstructive airways disease based on history and clinical examination. Albert's method includes an offset term to estimate an adjusted likelihood ratio for combinations of tests. Spiegelhalter and Knill-Jones method uses the unadjusted likelihood ratio for each test as a predictor and computes shrinkage factors to allow for interdependence. Knottnerus' method differs from the other methods because it requires sequencing of tests, which limits its application to situations where there are few tests and substantial data. Although parameter estimates differed between the models, predicted "posttest" probabilities were generally similar. Construction of predictive models using logistic regression is preferred to the independence Bayes' approach when it is important to adjust for dependency of tests errors. Methods to estimate adjusted likelihood ratios from predictive models should be considered in preference to a standard logistic regression model to facilitate ease of interpretation and application. Albert's method provides the most straightforward approach.

A comparison of three methods of assessing differential item functioning (DIF) in the Hospital Anxiety Depression Scale: ordinal logistic regression, Rasch analysis and the Mantel chi-square procedure.

PubMed

Cameron, Isobel M; Scott, Neil W; Adler, Mats; Reid, Ian C

2014-12-01

It is important for clinical practice and research that measurement scales of well-being and quality of life exhibit only minimal differential item functioning (DIF). DIF occurs where different groups of people endorse items in a scale to different extents after being matched by the intended scale attribute. We investigate the equivalence or otherwise of common methods of assessing DIF. Three methods of measuring age- and sex-related DIF (ordinal logistic regression, Rasch analysis and Mantel χ(2) procedure) were applied to Hospital Anxiety Depression Scale (HADS) data pertaining to a sample of 1,068 patients consulting primary care practitioners. Three items were flagged by all three approaches as having either age- or sex-related DIF with a consistent direction of effect; a further three items identified did not meet stricter criteria for important DIF using at least one method. When applying strict criteria for significant DIF, ordinal logistic regression was slightly less sensitive. Ordinal logistic regression, Rasch analysis and contingency table methods yielded consistent results when identifying DIF in the HADS depression and HADS anxiety scales. Regardless of methods applied, investigators should use a combination of statistical significance, magnitude of the DIF effect and investigator judgement when interpreting the results.

Extreme Sparse Multinomial Logistic Regression: A Fast and Robust Framework for Hyperspectral Image Classification

NASA Astrophysics Data System (ADS)

Cao, Faxian; Yang, Zhijing; Ren, Jinchang; Ling, Wing-Kuen; Zhao, Huimin; Marshall, Stephen

2017-12-01

Although the sparse multinomial logistic regression (SMLR) has provided a useful tool for sparse classification, it suffers from inefficacy in dealing with high dimensional features and manually set initial regressor values. This has significantly constrained its applications for hyperspectral image (HSI) classification. In order to tackle these two drawbacks, an extreme sparse multinomial logistic regression (ESMLR) is proposed for effective classification of HSI. First, the HSI dataset is projected to a new feature space with randomly generated weight and bias. Second, an optimization model is established by the Lagrange multiplier method and the dual principle to automatically determine a good initial regressor for SMLR via minimizing the training error and the regressor value. Furthermore, the extended multi-attribute profiles (EMAPs) are utilized for extracting both the spectral and spatial features. A combinational linear multiple features learning (MFL) method is proposed to further enhance the features extracted by ESMLR and EMAPs. Finally, the logistic regression via the variable splitting and the augmented Lagrangian (LORSAL) is adopted in the proposed framework for reducing the computational time. Experiments are conducted on two well-known HSI datasets, namely the Indian Pines dataset and the Pavia University dataset, which have shown the fast and robust performance of the proposed ESMLR framework.

Latin hypercube approach to estimate uncertainty in ground water vulnerability

USGS Publications Warehouse

Gurdak, J.J.; McCray, J.E.; Thyne, G.; Qi, S.L.

2007-01-01

A methodology is proposed to quantify prediction uncertainty associated with ground water vulnerability models that were developed through an approach that coupled multivariate logistic regression with a geographic information system (GIS). This method uses Latin hypercube sampling (LHS) to illustrate the propagation of input error and estimate uncertainty associated with the logistic regression predictions of ground water vulnerability. Central to the proposed method is the assumption that prediction uncertainty in ground water vulnerability models is a function of input error propagation from uncertainty in the estimated logistic regression model coefficients (model error) and the values of explanatory variables represented in the GIS (data error). Input probability distributions that represent both model and data error sources of uncertainty were simultaneously sampled using a Latin hypercube approach with logistic regression calculations of probability of elevated nonpoint source contaminants in ground water. The resulting probability distribution represents the prediction intervals and associated uncertainty of the ground water vulnerability predictions. The method is illustrated through a ground water vulnerability assessment of the High Plains regional aquifer. Results of the LHS simulations reveal significant prediction uncertainties that vary spatially across the regional aquifer. Additionally, the proposed method enables a spatial deconstruction of the prediction uncertainty that can lead to improved prediction of ground water vulnerability. ?? 2007 National Ground Water Association.

Estimation of Magnitude and Frequency of Floods for Streams on the Island of Oahu, Hawaii

USGS Publications Warehouse

Wong, Michael F.

1994-01-01

This report describes techniques for estimating the magnitude and frequency of floods for the island of Oahu. The log-Pearson Type III distribution and methodology recommended by the Interagency Committee on Water Data was used to determine the magnitude and frequency of floods at 79 gaging stations that had 11 to 72 years of record. Multiple regression analysis was used to construct regression equations to transfer the magnitude and frequency information from gaged sites to ungaged sites. Oahu was divided into three hydrologic regions to define relations between peak discharge and drainage-basin and climatic characteristics. Regression equations are provided to estimate the 2-, 5-, 10-, 25-, 50-, and 100-year peak discharges at ungaged sites. Significant basin and climatic characteristics included in the regression equations are drainage area, median annual rainfall, and the 2-year, 24-hour rainfall intensity. Drainage areas for sites used in this study ranged from 0.03 to 45.7 square miles. Standard error of prediction for the regression equations ranged from 34 to 62 percent. Peak-discharge data collected through water year 1988, geographic information system (GIS) technology, and generalized least-squares regression were used in the analyses. The use of GIS seems to be a more flexible and consistent means of defining and calculating basin and climatic characteristics than using manual methods. Standard errors of estimate for the regression equations in this report are an average of 8 percent less than those published in previous studies.

Anthropometric Variables Accurately Predict Dual Energy X-Ray Absorptiometric-Derived Body Composition and Can Be Used to Screen for Diabetes

PubMed Central

Yavari, Reza; McEntee, Erin; McEntee, Michael; Brines, Michael

2011-01-01

The current world-wide epidemic of obesity has stimulated interest in developing simple screening methods to identify individuals with undiagnosed diabetes mellitus type 2 (DM2) or metabolic syndrome (MS). Prior work utilizing body composition obtained by sophisticated technology has shown that the ratio of abdominal fat to total fat is a good predictor for DM2 or MS. The goals of this study were to determine how well simple anthropometric variables predict the fat mass distribution as determined by dual energy x-ray absorptometry (DXA), and whether these are useful to screen for DM2 or MS within a population. To accomplish this, the body composition of 341 females spanning a wide range of body mass indices and with a 23% prevalence of DM2 and MS was determined using DXA. Stepwise linear regression models incorporating age, weight, height, waistline, and hipline predicted DXA body composition (i.e., fat mass, trunk fat, fat free mass, and total mass) with good accuracy. Using body composition as independent variables, nominal logistic regression was then performed to estimate the probability of DM2. The results show good discrimination with the receiver operating characteristic (ROC) having an area under the curve (AUC) of 0.78. The anthropometrically-derived body composition equations derived from the full DXA study group were then applied to a group of 1153 female patients selected from a general endocrinology practice. Similar to the smaller study group, the ROC from logistical regression using body composition had an AUC of 0.81 for the detection of DM2. These results are superior to screening based on questionnaires and compare favorably with published data derived from invasive testing, e.g., hemoglobin A1c. This anthropometric approach offers promise for the development of simple, inexpensive, non-invasive screening to identify individuals with metabolic dysfunction within large populations. PMID:21915276

Modeling statistics and kinetics of the natural aggregation structures and processes with the solution of generalized logistic equation

NASA Astrophysics Data System (ADS)

Maslov, Lev A.; Chebotarev, Vladimir I.

2017-02-01

The generalized logistic equation is proposed to model kinetics and statistics of natural processes such as earthquakes, forest fires, floods, landslides, and many others. This equation has the form dN(A)/dA = s dot (1-N(A)) dot N(A)q dot A-α, q>0q>0 and A>0A>0 is the size of an element of a structure, and α≥0. The equation contains two exponents α and q taking into account two important properties of elements of a system: their fractal geometry, and their ability to interact either to enhance or to damp the process of aggregation. The function N(A)N(A) can be understood as an approximation to the number of elements the size of which is less than AA. The function dN(A)/dAdN(A)/dA where N(A)N(A) is the general solution of this equation for q=1 is a product of an increasing bounded function and power-law function with stretched exponential cut-off. The relation with Tsallis non-extensive statistics is demonstrated by solving the generalized logistic equation for q>0q>0. In the case 01q>1 it models sub-additive structures. The Gutenberg-Richter (G-R) formula results from interpretation of empirical data as a straight line in the area of stretched exponent with small α. The solution is applied for modeling distribution of foreshocks and aftershocks in the regions of Napa Valley 2014, and Sumatra 2004 earthquakes fitting the observed data well, both qualitatively and quantitatively.

The PIT-trap-A "model-free" bootstrap procedure for inference about regression models with discrete, multivariate responses.

PubMed

Warton, David I; Thibaut, Loïc; Wang, Yi Alice

2017-01-01

Bootstrap methods are widely used in statistics, and bootstrapping of residuals can be especially useful in the regression context. However, difficulties are encountered extending residual resampling to regression settings where residuals are not identically distributed (thus not amenable to bootstrapping)-common examples including logistic or Poisson regression and generalizations to handle clustered or multivariate data, such as generalised estimating equations. We propose a bootstrap method based on probability integral transform (PIT-) residuals, which we call the PIT-trap, which assumes data come from some marginal distribution F of known parametric form. This method can be understood as a type of "model-free bootstrap", adapted to the problem of discrete and highly multivariate data. PIT-residuals have the key property that they are (asymptotically) pivotal. The PIT-trap thus inherits the key property, not afforded by any other residual resampling approach, that the marginal distribution of data can be preserved under PIT-trapping. This in turn enables the derivation of some standard bootstrap properties, including second-order correctness of pivotal PIT-trap test statistics. In multivariate data, bootstrapping rows of PIT-residuals affords the property that it preserves correlation in data without the need for it to be modelled, a key point of difference as compared to a parametric bootstrap. The proposed method is illustrated on an example involving multivariate abundance data in ecology, and demonstrated via simulation to have improved properties as compared to competing resampling methods.

The PIT-trap—A “model-free” bootstrap procedure for inference about regression models with discrete, multivariate responses

PubMed Central

Thibaut, Loïc; Wang, Yi Alice

2017-01-01

Bootstrap methods are widely used in statistics, and bootstrapping of residuals can be especially useful in the regression context. However, difficulties are encountered extending residual resampling to regression settings where residuals are not identically distributed (thus not amenable to bootstrapping)—common examples including logistic or Poisson regression and generalizations to handle clustered or multivariate data, such as generalised estimating equations. We propose a bootstrap method based on probability integral transform (PIT-) residuals, which we call the PIT-trap, which assumes data come from some marginal distribution F of known parametric form. This method can be understood as a type of “model-free bootstrap”, adapted to the problem of discrete and highly multivariate data. PIT-residuals have the key property that they are (asymptotically) pivotal. The PIT-trap thus inherits the key property, not afforded by any other residual resampling approach, that the marginal distribution of data can be preserved under PIT-trapping. This in turn enables the derivation of some standard bootstrap properties, including second-order correctness of pivotal PIT-trap test statistics. In multivariate data, bootstrapping rows of PIT-residuals affords the property that it preserves correlation in data without the need for it to be modelled, a key point of difference as compared to a parametric bootstrap. The proposed method is illustrated on an example involving multivariate abundance data in ecology, and demonstrated via simulation to have improved properties as compared to competing resampling methods. PMID:28738071

Novel CPR system that predicts return of spontaneous circulation from amplitude spectral area before electric shock in ventricular fibrillation.

PubMed

Nakagawa, Yoshihide; Amino, Mari; Inokuchi, Sadaki; Hayashi, Satoshi; Wakabayashi, Tsutomu; Noda, Tatsuya

2017-04-01

Amplitude spectral area (AMSA), an index for analysing ventricular fibrillation (VF) waveforms, is thought to predict the return of spontaneous circulation (ROSC) after electric shocks, but its validity is unconfirmed. We developed an equation to predict ROSC, where the change in AMSA (ΔAMSA) is added to AMSA measured immediately before the first shock (AMSA1). We examine the validity of this equation by comparing it with the conventional AMSA1-only equation. We retrospectively investigated 285 VF patients given prehospital electric shocks by emergency medical services. ΔAMSA was calculated by subtracting AMSA1 from last AMSA immediately before the last prehospital electric shock. Multivariate logistic regression analysis was performed using post-shock ROSC as a dependent variable. Analysis data were subjected to receiver operating characteristic curve analysis, goodness-of-fit testing using a likelihood ratio test, and the bootstrap method. AMSA1 (odds ratio (OR) 1.151, 95% confidence interval (CI) 1.086-1.220) and ΔAMSA (OR 1.289, 95% CI 1.156-1.438) were independent factors influencing ROSC induction by electric shock. Area under the curve (AUC) for predicting ROSC was 0.851 for AMSA1-only and 0.891 for AMSA1+ΔAMSA. Compared with the AMSA1-only equation, the AMSA1+ΔAMSA equation had significantly better goodness-of-fit (likelihood ratio test P<0.001) and showed good fit in the bootstrap method. Post-shock ROSC was accurately predicted by adding ΔAMSA to AMSA1. AMSA-based ROSC prediction enables application of electric shock to only those patients with high probability of ROSC, instead of interrupting chest compressions and delivering unnecessary shocks to patients with low probability of ROSC. Copyright © 2017 Elsevier B.V. All rights reserved.

Validation of Core Temperature Estimation Algorithm

DTIC Science & Technology

2016-01-29

plot of observed versus estimated core temperature with the line of identity (dashed) and the least squares regression line (solid) and line equation...estimated PSI with the line of identity (dashed) and the least squares regression line (solid) and line equation in the top left corner. (b) Bland...for comparison. The root mean squared error (RMSE) was also computed, as given by Equation 2.

Methods for estimating flood frequency in Montana based on data through water year 1998

USGS Publications Warehouse

Parrett, Charles; Johnson, Dave R.

2004-01-01

Annual peak discharges having recurrence intervals of 2, 5, 10, 25, 50, 100, 200, and 500 years (T-year floods) were determined for 660 gaged sites in Montana and in adjacent areas of Idaho, Wyoming, and Canada, based on data through water year 1998. The updated flood-frequency information was subsequently used in regression analyses, either ordinary or generalized least squares, to develop equations relating T-year floods to various basin and climatic characteristics, equations relating T-year floods to active-channel width, and equations relating T-year floods to bankfull width. The equations can be used to estimate flood frequency at ungaged sites. Montana was divided into eight regions, within which flood characteristics were considered to be reasonably homogeneous, and the three sets of regression equations were developed for each region. A measure of the overall reliability of the regression equations is the average standard error of prediction. The average standard errors of prediction for the equations based on basin and climatic characteristics ranged from 37.4 percent to 134.1 percent. Average standard errors of prediction for the equations based on active-channel width ranged from 57.2 percent to 141.3 percent. Average standard errors of prediction for the equations based on bankfull width ranged from 63.1 percent to 155.5 percent. In most regions, the equations based on basin and climatic characteristics generally had smaller average standard errors of prediction than equations based on active-channel or bankfull width. An exception was the Southeast Plains Region, where all equations based on active-channel width had smaller average standard errors of prediction than equations based on basin and climatic characteristics or bankfull width. Methods for weighting estimates derived from the basin- and climatic-characteristic equations and the channel-width equations also were developed. The weights were based on the cross correlation of residuals from the different methods and the average standard errors of prediction. When all three methods were combined, the average standard errors of prediction ranged from 37.4 percent to 120.2 percent. Weighting of estimates reduced the standard errors of prediction for all T-year flood estimates in four regions, reduced the standard errors of prediction for some T-year flood estimates in two regions, and provided no reduction in average standard error of prediction in two regions. A computer program for solving the regression equations, weighting estimates, and determining reliability of individual estimates was developed and placed on the USGS Montana District World Wide Web page. A new regression method, termed Region of Influence regression, also was tested. Test results indicated that the Region of Influence method was not as reliable as the regional equations based on generalized least squares regression. Two additional methods for estimating flood frequency at ungaged sites located on the same streams as gaged sites also are described. The first method, based on a drainage-area-ratio adjustment, is intended for use on streams where the ungaged site of interest is located near a gaged site. The second method, based on interpolation between gaged sites, is intended for use on streams that have two or more streamflow-gaging stations.

Flood-frequency prediction methods for unregulated streams of Tennessee, 2000

USGS Publications Warehouse

Law, George S.; Tasker, Gary D.

2003-01-01

Up-to-date flood-frequency prediction methods for unregulated, ungaged rivers and streams of Tennessee have been developed. Prediction methods include the regional-regression method and the newer region-of-influence method. The prediction methods were developed using stream-gage records from unregulated streams draining basins having from 1 percent to about 30 percent total impervious area. These methods, however, should not be used in heavily developed or storm-sewered basins with impervious areas greater than 10 percent. The methods can be used to estimate 2-, 5-, 10-, 25-, 50-, 100-, and 500-year recurrence-interval floods of most unregulated rural streams in Tennessee. A computer application was developed that automates the calculation of flood frequency for unregulated, ungaged rivers and streams of Tennessee. Regional-regression equations were derived by using both single-variable and multivariable regional-regression analysis. Contributing drainage area is the explanatory variable used in the single-variable equations. Contributing drainage area, main-channel slope, and a climate factor are the explanatory variables used in the multivariable equations. Deleted-residual standard error for the single-variable equations ranged from 32 to 65 percent. Deleted-residual standard error for the multivariable equations ranged from 31 to 63 percent. These equations are included in the computer application to allow easy comparison of results produced by the different methods. The region-of-influence method calculates multivariable regression equations for each ungaged site and recurrence interval using basin characteristics from 60 similar sites selected from the study area. Explanatory variables that may be used in regression equations computed by the region-of-influence method include contributing drainage area, main-channel slope, a climate factor, and a physiographic-region factor. Deleted-residual standard error for the region-of-influence method tended to be only slightly smaller than those for the regional-regression method and ranged from 27 to 62 percent.

Techniques for estimating magnitude and frequency of peak flows for Pennsylvania streams

USGS Publications Warehouse

Stuckey, Marla H.; Reed, Lloyd A.

2000-01-01

Regression equations for estimating the magnitude and frequency of floods on ungaged streams in Pennsylvania with drainage areas less that 2,000 square miles were developed on the basis of peak-flow data collected at 313 streamflow-gaging stations. All streamflow-gaging stations used in the development of the equations had 10 or more years of record and include active and discontinued continuous-record and crest-stage partial-record streamflow-gaging stations. Regional regression equations were developed for flood flows expected every 10, 25, 50, 100, and 500 years by the use of a weighted multiple linear regression model.The State was divided into two regions. The largest region, Region A, encompasses about 78 percent of Pennsylvania. The smaller region, Region B, includes only the northwestern part of the State. Basin characteristics used in the regression equations for Region A are drainage area, percentage of forest cover, percentage of urban development, percentage of basin underlain by carbonate bedrock, and percentage of basin controlled by lakes, swamps, and reservoirs. Basin characteristics used in the regression equations for Region B are drainage area and percentage of basin controlled by lakes, swamps, and reservoirs. The coefficient of determination (R2) values for the five flood-frequency equations for Region A range from 0.93 to 0.82, and for Region B, the range is from 0.96 to 0.89.While the regression equations can be used to predict the magnitude and frequency of peak flows for most streams in the State, they should not be used for streams with drainage areas greater than 2,000 square miles or less than 1.5 square miles, for streams that drain extensively mined areas, or for stream reaches immediately below flood-control reservoirs. In addition, the equations presented for Region B should not be used if the stream drains a basin with more than 5 percent urban development.

Estimation of flood discharges at selected annual exceedance probabilities for unregulated, rural streams in Vermont, with a section on Vermont regional skew regression

USGS Publications Warehouse

Olson, Scott A.; with a section by Veilleux, Andrea G.

2014-01-01

This report provides estimates of flood discharges at selected annual exceedance probabilities (AEPs) for streamgages in and adjacent to Vermont and equations for estimating flood discharges at AEPs of 50-, 20-, 10-, 4-, 2-, 1-, 0.5-, and 0.2-percent (recurrence intervals of 2-, 5-, 10-, 25-, 50-, 100-, 200-, and 500-years, respectively) for ungaged, unregulated, rural streams in Vermont. The equations were developed using generalized least-squares regression. Flood-frequency and drainage-basin characteristics from 145 streamgages were used in developing the equations. The drainage-basin characteristics used as explanatory variables in the regression equations include drainage area, percentage of wetland area, and the basin-wide mean of the average annual precipitation. The average standard errors of prediction for estimating the flood discharges at the 50-, 20-, 10-, 4-, 2-, 1-, 0.5-, and 0.2-percent AEP with these equations are 34.9, 36.0, 38.7, 42.4, 44.9, 47.3, 50.7, and 55.1 percent, respectively. Flood discharges at selected AEPs for streamgages were computed by using the Expected Moments Algorithm. To improve estimates of the flood discharges for given exceedance probabilities at streamgages in Vermont, a new generalized skew coefficient was developed. The new generalized skew for the region is a constant, 0.44. The mean square error of the generalized skew coefficient is 0.078. This report describes a technique for using results from the regression equations to adjust an AEP discharge computed from a streamgage record. This report also describes a technique for using a drainage-area adjustment to estimate flood discharge at a selected AEP for an ungaged site upstream or downstream from a streamgage. The final regression equations and the flood-discharge frequency data used in this study will be available in StreamStats. StreamStats is a World Wide Web application providing automated regression-equation solutions for user-selected sites on streams.

Predictors of postoperative outcomes of cubital tunnel syndrome treatments using multiple logistic regression analysis.

PubMed

Suzuki, Taku; Iwamoto, Takuji; Shizu, Kanae; Suzuki, Katsuji; Yamada, Harumoto; Sato, Kazuki

2017-05-01

This retrospective study was designed to investigate prognostic factors for postoperative outcomes for cubital tunnel syndrome (CubTS) using multiple logistic regression analysis with a large number of patients. Eighty-three patients with CubTS who underwent surgeries were enrolled. The following potential prognostic factors for disease severity were selected according to previous reports: sex, age, type of surgery, disease duration, body mass index, cervical lesion, presence of diabetes mellitus, Workers' Compensation status, preoperative severity, and preoperative electrodiagnostic testing. Postoperative severity of disease was assessed 2 years after surgery by Messina's criteria which is an outcome measure specifically for CubTS. Bivariate analysis was performed to select candidate prognostic factors for multiple linear regression analyses. Multiple logistic regression analysis was conducted to identify the association between postoperative severity and selected prognostic factors. Both bivariate and multiple linear regression analysis revealed only preoperative severity as an independent risk factor for poor prognosis, while other factors did not show any significant association. Although conflicting results exist regarding prognosis of CubTS, this study supports evidence from previous studies and concludes early surgical intervention portends the most favorable prognosis. Copyright © 2017 The Japanese Orthopaedic Association. Published by Elsevier B.V. All rights reserved.

Predictive equations for the estimation of body size in seals and sea lions (Carnivora: Pinnipedia)

PubMed Central

Churchill, Morgan; Clementz, Mark T; Kohno, Naoki

2014-01-01

Body size plays an important role in pinniped ecology and life history. However, body size data is often absent for historical, archaeological, and fossil specimens. To estimate the body size of pinnipeds (seals, sea lions, and walruses) for today and the past, we used 14 commonly preserved cranial measurements to develop sets of single variable and multivariate predictive equations for pinniped body mass and total length. Principal components analysis (PCA) was used to test whether separate family specific regressions were more appropriate than single predictive equations for Pinnipedia. The influence of phylogeny was tested with phylogenetic independent contrasts (PIC). The accuracy of these regressions was then assessed using a combination of coefficient of determination, percent prediction error, and standard error of estimation. Three different methods of multivariate analysis were examined: bidirectional stepwise model selection using Akaike information criteria; all-subsets model selection using Bayesian information criteria (BIC); and partial least squares regression. The PCA showed clear discrimination between Otariidae (fur seals and sea lions) and Phocidae (earless seals) for the 14 measurements, indicating the need for family-specific regression equations. The PIC analysis found that phylogeny had a minor influence on relationship between morphological variables and body size. The regressions for total length were more accurate than those for body mass, and equations specific to Otariidae were more accurate than those for Phocidae. Of the three multivariate methods, the all-subsets approach required the fewest number of variables to estimate body size accurately. We then used the single variable predictive equations and the all-subsets approach to estimate the body size of two recently extinct pinniped taxa, the Caribbean monk seal (Monachus tropicalis) and the Japanese sea lion (Zalophus japonicus). Body size estimates using single variable regressions generally under or over-estimated body size; however, the all-subset regression produced body size estimates that were close to historically recorded body length for these two species. This indicates that the all-subset regression equations developed in this study can estimate body size accurately. PMID:24916814

The National Flood Frequency Program, version 3 : a computer program for estimating magnitude and frequency of floods for ungaged sites

USGS Publications Warehouse

Ries, Kernell G.; Crouse, Michele Y.

2002-01-01

For many years, the U.S. Geological Survey (USGS) has been developing regional regression equations for estimating flood magnitude and frequency at ungaged sites. These regression equations are used to transfer flood characteristics from gaged to ungaged sites through the use of watershed and climatic characteristics as explanatory or predictor variables. Generally, these equations have been developed on a Statewide or metropolitan-area basis as part of cooperative study programs with specific State Departments of Transportation. In 1994, the USGS released a computer program titled the National Flood Frequency Program (NFF), which compiled all the USGS available regression equations for estimating the magnitude and frequency of floods in the United States and Puerto Rico. NFF was developed in cooperation with the Federal Highway Administration and the Federal Emergency Management Agency. Since the initial release of NFF, the USGS has produced new equations for many areas of the Nation. A new version of NFF has been developed that incorporates these new equations and provides additional functionality and ease of use. NFF version 3 provides regression-equation estimates of flood-peak discharges for unregulated rural and urban watersheds, flood-frequency plots, and plots of typical flood hydrographs for selected recurrence intervals. The Program also provides weighting techniques to improve estimates of flood-peak discharges for gaging stations and ungaged sites. The information provided by NFF should be useful to engineers and hydrologists for planning and design applications. This report describes the flood-regionalization techniques used in NFF and provides guidance on the applicability and limitations of the techniques. The NFF software and the documentation for the regression equations included in NFF are available at http://water.usgs.gov/software/nff.html.

Semistable extremal ground states for nonlinear evolution equations in unbounded domains

NASA Astrophysics Data System (ADS)

Rodríguez-Bernal, Aníbal; Vidal-López, Alejandro

2008-02-01

In this paper we show that dissipative reaction-diffusion equations in unbounded domains posses extremal semistable ground states equilibria, which bound asymptotically the global dynamics. Uniqueness of such positive ground state and their approximation by extremal equilibria in bounded domains is also studied. The results are then applied to the important case of logistic equations.

eGFRs from Asian-modified CKD-EPI and Chinese-modified CKD-EPI equations were associated better with hypertensive target organ damage in the community-dwelling elderly Chinese: the Northern Shanghai Study.

PubMed

Ji, Hongwei; Zhang, Han; Xiong, Jing; Yu, Shikai; Chi, Chen; Bai, Bin; Li, Jue; Blacher, Jacques; Zhang, Yi; Xu, Yawei

2017-01-01

With increasing age, estimated glomerular filtration rate (eGFR) decline is a frequent manifestation and is strongly associated with other preclinical target organ damage (TOD). In literature, many equations exist in assessing patients' eGFR. However, these equations were mainly derived and validated in the population from Western countries, which equation should be used for risk stratification in the Chinese population remains unclear, as well as their comparison. Considering that TOD is a good marker for risk stratification in the elderly, in this analysis, we aimed to investigate whether the recent eGFR equations derived from Asian and Chinese are better associated with preclinical TOD than the other equations in elderly Chinese. A total of 1,599 community-dwelling elderly participants (age >65 years) in northern Shanghai were prospectively recruited from June 2014 to August 2015. Conventional cardiovascular risk factors were assessed, and hypertensive TOD including left ventricular mass index (LVMI), carotid-femoral pulse wave velocity (cf-PWV), carotid intima-media thickness (IMT), ankle-brachial index (ABI) and urine albumin to creatinine ratio (UACR) was evaluated for each participant. Participant's eGFR was calculated from the Modification of Diet in Renal Disease (MDRD), Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI), Chinese-abbreviated MDRD (c-aMDRD), Asian-modified CKD-EPI (aCKD-EPI) equation and Chinese-modified CKD-EPI (cCKD-EPI) equation. In multivariate regression analysis, only eGFRs from aCKD-EPI were significantly and inversely associated with carotid IMT ( P =0.005). In multivariate logistic models, decreased eGFR from all the equations were significantly associated with lower ABI ( P <0.001), microalbuminuria ( P =0.02 to P <0.001) and increased cf-PWV ( P <0.001). Only decreased eGFRs from aCKD-EPI and cCKD-EPI equations were significantly associated with increased IMT (both crude P <0.05). In the receiver operator characteristic (ROC) analysis, only aCKD-EPI and cCKD-EPI equations presented significant associations with all the listed preclinical TODs ( P -value from <0.05 to <0.001). In community-dwelling elderly Chinese, eGFRs from aCKD-EPI and cCKD-EPI equations are better associated with preclinical TOD. aCKD-EPI and cCKD-EPI equations should be preferred when making risk assessment.

A Logistic Regression Analysis of Turkey's 15-Year-Olds' Scoring above the OECD Average on the PISA'09 Reading Assessment

ERIC Educational Resources Information Center

Kasapoglu, Koray

2014-01-01

This study aims to investigate which factors are associated with Turkey's 15-year-olds' scoring above the OECD average (493) on the PISA'09 reading assessment. Collected from a total of 4,996 15-year-old students from Turkey, data were analyzed by logistic regression analysis in order to model the data of students who were split into two: (1)…

Estimating the Probability of Rare Events Occurring Using a Local Model Averaging.

PubMed

Chen, Jin-Hua; Chen, Chun-Shu; Huang, Meng-Fan; Lin, Hung-Chih

2016-10-01

In statistical applications, logistic regression is a popular method for analyzing binary data accompanied by explanatory variables. But when one of the two outcomes is rare, the estimation of model parameters has been shown to be severely biased and hence estimating the probability of rare events occurring based on a logistic regression model would be inaccurate. In this article, we focus on estimating the probability of rare events occurring based on logistic regression models. Instead of selecting a best model, we propose a local model averaging procedure based on a data perturbation technique applied to different information criteria to obtain different probability estimates of rare events occurring. Then an approximately unbiased estimator of Kullback-Leibler loss is used to choose the best one among them. We design complete simulations to show the effectiveness of our approach. For illustration, a necrotizing enterocolitis (NEC) data set is analyzed. © 2016 Society for Risk Analysis.

Evaluating the perennial stream using logistic regression in central Taiwan

NASA Astrophysics Data System (ADS)

Ruljigaljig, T.; Cheng, Y. S.; Lin, H. I.; Lee, C. H.; Yu, T. T.

2014-12-01

This study produces a perennial stream head potential map, based on a logistic regression method with a Geographic Information System (GIS). Perennial stream initiation locations, indicates the location of the groundwater and surface contact, were identified in the study area from field survey. The perennial stream potential map in central Taiwan was constructed using the relationship between perennial stream and their causative factors, such as Catchment area, slope gradient, aspect, elevation, groundwater recharge and precipitation. Here, the field surveys of 272 streams were determined in the study area. The areas under the curve for logistic regression methods were calculated as 0.87. The results illustrate the importance of catchment area and groundwater recharge as key factors within the model. The results obtained from the model within the GIS were then used to produce a map of perennial stream and estimate the location of perennial stream head.

An application in identifying high-risk populations in alternative tobacco product use utilizing logistic regression and CART: a heuristic comparison.

PubMed

Lei, Yang; Nollen, Nikki; Ahluwahlia, Jasjit S; Yu, Qing; Mayo, Matthew S

2015-04-09

Other forms of tobacco use are increasing in prevalence, yet most tobacco control efforts are aimed at cigarettes. In light of this, it is important to identify individuals who are using both cigarettes and alternative tobacco products (ATPs). Most previous studies have used regression models. We conducted a traditional logistic regression model and a classification and regression tree (CART) model to illustrate and discuss the added advantages of using CART in the setting of identifying high-risk subgroups of ATP users among cigarettes smokers. The data were collected from an online cross-sectional survey administered by Survey Sampling International between July 5, 2012 and August 15, 2012. Eligible participants self-identified as current smokers, African American, White, or Latino (of any race), were English-speaking, and were at least 25 years old. The study sample included 2,376 participants and was divided into independent training and validation samples for a hold out validation. Logistic regression and CART models were used to examine the important predictors of cigarettes + ATP users. The logistic regression model identified nine important factors: gender, age, race, nicotine dependence, buying cigarettes or borrowing, whether the price of cigarettes influences the brand purchased, whether the participants set limits on cigarettes per day, alcohol use scores, and discrimination frequencies. The C-index of the logistic regression model was 0.74, indicating good discriminatory capability. The model performed well in the validation cohort also with good discrimination (c-index = 0.73) and excellent calibration (R-square = 0.96 in the calibration regression). The parsimonious CART model identified gender, age, alcohol use score, race, and discrimination frequencies to be the most important factors. It also revealed interesting partial interactions. The c-index is 0.70 for the training sample and 0.69 for the validation sample. The misclassification rate was 0.342 for the training sample and 0.346 for the validation sample. The CART model was easier to interpret and discovered target populations that possess clinical significance. This study suggests that the non-parametric CART model is parsimonious, potentially easier to interpret, and provides additional information in identifying the subgroups at high risk of ATP use among cigarette smokers.

Determination of osteoporosis risk factors using a multiple logistic regression model in postmenopausal Turkish women.

PubMed

Akkus, Zeki; Camdeviren, Handan; Celik, Fatma; Gur, Ali; Nas, Kemal

2005-09-01

To determine the risk factors of osteoporosis using a multiple binary logistic regression method and to assess the risk variables for osteoporosis, which is a major and growing health problem in many countries. We presented a case-control study, consisting of 126 postmenopausal healthy women as control group and 225 postmenopausal osteoporotic women as the case group. The study was carried out in the Department of Physical Medicine and Rehabilitation, Dicle University, Diyarbakir, Turkey between 1999-2002. The data from the 351 participants were collected using a standard questionnaire that contains 43 variables. A multiple logistic regression model was then used to evaluate the data and to find the best regression model. We classified 80.1% (281/351) of the participants using the regression model. Furthermore, the specificity value of the model was 67% (84/126) of the control group while the sensitivity value was 88% (197/225) of the case group. We found the distribution of residual values standardized for final model to be exponential using the Kolmogorow-Smirnow test (p=0.193). The receiver operating characteristic curve was found successful to predict patients with risk for osteoporosis. This study suggests that low levels of dietary calcium intake, physical activity, education, and longer duration of menopause are independent predictors of the risk of low bone density in our population. Adequate dietary calcium intake in combination with maintaining a daily physical activity, increasing educational level, decreasing birth rate, and duration of breast-feeding may contribute to healthy bones and play a role in practical prevention of osteoporosis in Southeast Anatolia. In addition, the findings of the present study indicate that the use of multivariate statistical method as a multiple logistic regression in osteoporosis, which maybe influenced by many variables, is better than univariate statistical evaluation.

Classification and regression tree analysis of acute-on-chronic hepatitis B liver failure: Seeing the forest for the trees.

PubMed

Shi, K-Q; Zhou, Y-Y; Yan, H-D; Li, H; Wu, F-L; Xie, Y-Y; Braddock, M; Lin, X-Y; Zheng, M-H

2017-02-01

At present, there is no ideal model for predicting the short-term outcome of patients with acute-on-chronic hepatitis B liver failure (ACHBLF). This study aimed to establish and validate a prognostic model by using the classification and regression tree (CART) analysis. A total of 1047 patients from two separate medical centres with suspected ACHBLF were screened in the study, which were recognized as derivation cohort and validation cohort, respectively. CART analysis was applied to predict the 3-month mortality of patients with ACHBLF. The accuracy of the CART model was tested using the area under the receiver operating characteristic curve, which was compared with the model for end-stage liver disease (MELD) score and a new logistic regression model. CART analysis identified four variables as prognostic factors of ACHBLF: total bilirubin, age, serum sodium and INR, and three distinct risk groups: low risk (4.2%), intermediate risk (30.2%-53.2%) and high risk (81.4%-96.9%). The new logistic regression model was constructed with four independent factors, including age, total bilirubin, serum sodium and prothrombin activity by multivariate logistic regression analysis. The performances of the CART model (0.896), similar to the logistic regression model (0.914, P=.382), exceeded that of MELD score (0.667, P<.001). The results were confirmed in the validation cohort. We have developed and validated a novel CART model superior to MELD for predicting three-month mortality of patients with ACHBLF. Thus, the CART model could facilitate medical decision-making and provide clinicians with a validated practical bedside tool for ACHBLF risk stratification. © 2016 John Wiley & Sons Ltd.

Identification of immune correlates of protection in Shigella infection by application of machine learning.

PubMed

Arevalillo, Jorge M; Sztein, Marcelo B; Kotloff, Karen L; Levine, Myron M; Simon, Jakub K

2017-10-01

Immunologic correlates of protection are important in vaccine development because they give insight into mechanisms of protection, assist in the identification of promising vaccine candidates, and serve as endpoints in bridging clinical vaccine studies. Our goal is the development of a methodology to identify immunologic correlates of protection using the Shigella challenge as a model. The proposed methodology utilizes the Random Forests (RF) machine learning algorithm as well as Classification and Regression Trees (CART) to detect immune markers that predict protection, identify interactions between variables, and define optimal cutoffs. Logistic regression modeling is applied to estimate the probability of protection and the confidence interval (CI) for such a probability is computed by bootstrapping the logistic regression models. The results demonstrate that the combination of Classification and Regression Trees and Random Forests complements the standard logistic regression and uncovers subtle immune interactions. Specific levels of immunoglobulin IgG antibody in blood on the day of challenge predicted protection in 75% (95% CI 67-86). Of those subjects that did not have blood IgG at or above a defined threshold, 100% were protected if they had IgA antibody secreting cells above a defined threshold. Comparison with the results obtained by applying only logistic regression modeling with standard Akaike Information Criterion for model selection shows the usefulness of the proposed method. Given the complexity of the immune system, the use of machine learning methods may enhance traditional statistical approaches. When applied together, they offer a novel way to quantify important immune correlates of protection that may help the development of vaccines. Copyright © 2017 Elsevier Inc. All rights reserved.

The quest for conditional independence in prospectivity modeling: weights-of-evidence, boost weights-of-evidence, and logistic regression

NASA Astrophysics Data System (ADS)

Schaeben, Helmut; Semmler, Georg

2016-09-01

The objective of prospectivity modeling is prediction of the conditional probability of the presence T = 1 or absence T = 0 of a target T given favorable or prohibitive predictors B, or construction of a two classes 0,1 classification of T. A special case of logistic regression called weights-of-evidence (WofE) is geologists' favorite method of prospectivity modeling due to its apparent simplicity. However, the numerical simplicity is deceiving as it is implied by the severe mathematical modeling assumption of joint conditional independence of all predictors given the target. General weights of evidence are explicitly introduced which are as simple to estimate as conventional weights, i.e., by counting, but do not require conditional independence. Complementary to the regression view is the classification view on prospectivity modeling. Boosting is the construction of a strong classifier from a set of weak classifiers. From the regression point of view it is closely related to logistic regression. Boost weights-of-evidence (BoostWofE) was introduced into prospectivity modeling to counterbalance violations of the assumption of conditional independence even though relaxation of modeling assumptions with respect to weak classifiers was not the (initial) purpose of boosting. In the original publication of BoostWofE a fabricated dataset was used to "validate" this approach. Using the same fabricated dataset it is shown that BoostWofE cannot generally compensate lacking conditional independence whatever the consecutively processing order of predictors. Thus the alleged features of BoostWofE are disproved by way of counterexamples, while theoretical findings are confirmed that logistic regression including interaction terms can exactly compensate violations of joint conditional independence if the predictors are indicators.

Regression equations for estimating flood flows for the 2-, 10-, 25-, 50-, 100-, and 500-Year recurrence intervals in Connecticut

USGS Publications Warehouse

Ahearn, Elizabeth A.

2004-01-01

Multiple linear-regression equations were developed to estimate the magnitudes of floods in Connecticut for recurrence intervals ranging from 2 to 500 years. The equations can be used for nonurban, unregulated stream sites in Connecticut with drainage areas ranging from about 2 to 715 square miles. Flood-frequency data and hydrologic characteristics from 70 streamflow-gaging stations and the upstream drainage basins were used to develop the equations. The hydrologic characteristics?drainage area, mean basin elevation, and 24-hour rainfall?are used in the equations to estimate the magnitude of floods. Average standard errors of prediction for the equations are 31.8, 32.7, 34.4, 35.9, 37.6 and 45.0 percent for the 2-, 10-, 25-, 50-, 100-, and 500-year recurrence intervals, respectively. Simplified equations using only one hydrologic characteristic?drainage area?also were developed. The regression analysis is based on generalized least-squares regression techniques. Observed flows (log-Pearson Type III analysis of the annual maximum flows) from five streamflow-gaging stations in urban basins in Connecticut were compared to flows estimated from national three-parameter and seven-parameter urban regression equations. The comparison shows that the three- and seven- parameter equations used in conjunction with the new statewide equations generally provide reasonable estimates of flood flows for urban sites in Connecticut, although a national urban flood-frequency study indicated that the three-parameter equations significantly underestimated flood flows in many regions of the country. Verification of the accuracy of the three-parameter or seven-parameter national regression equations using new data from Connecticut stations was beyond the scope of this study. A technique for calculating flood flows at streamflow-gaging stations using a weighted average also is described. Two estimates of flood flows?one estimate based on the log-Pearson Type III analyses of the annual maximum flows at the gaging station, and the other estimate from the regression equation?are weighted together based on the years of record at the gaging station and the equivalent years of record value determined from the regression. Weighted averages of flood flows for the 2-, 10-, 25-, 50-, 100-, and 500-year recurrence intervals are tabulated for the 70 streamflow-gaging stations used in the regression analysis. Generally, weighted averages give the most accurate estimate of flood flows at gaging stations. An evaluation of the Connecticut's streamflow-gaging network was performed to determine whether the spatial coverage and range of geographic and hydrologic conditions are adequately represented for transferring flood characteristics from gaged to ungaged sites. Fifty-one of 54 stations in the current (2004) network support one or more flood needs of federal, state, and local agencies. Twenty-five of 54 stations in the current network are considered high-priority stations by the U.S. Geological Survey because of their contribution to the longterm understanding of floods, and their application for regionalflood analysis. Enhancements to the network to improve overall effectiveness for regionalization can be made by increasing the spatial coverage of gaging stations, establishing stations in regions of the state that are not well-represented, and adding stations in basins with drainage area sizes not represented. Additionally, the usefulness of the network for characterizing floods can be maintained and improved by continuing operation at the current stations because flood flows can be more accurately estimated at stations with continuous, long-term record.

Validation of risk assessment scoring systems for an audit of elective surgery for gastrointestinal cancer in elderly patients: an audit.

PubMed

Wakabayashi, Hisao; Sano, Takanori; Yachida, Shinichi; Okano, Keiichi; Izuishi, Kunihiko; Suzuki, Yasuyuki

2007-10-01

The goal of this study was to validate the usefulness of risk assessment scoring systems for a surgical audit in elective digestive surgery for elderly patients. The validated scoring systems used were the Physiological and Operative Severity Score for enUmeration of Mortality and morbidity (POSSUM) and the Portsmouth predictor equation for mortality (P-POSSUM). This study involved 153 consecutive patients aged 75 years and older who underwent elective gastric or colorectal surgery between July 2004 and June 2006. A retrospective analysis was performed on data collected prior to each surgery. The predicted mortality and morbidity risks were calculated using each of the scoring systems and were used to obtain the observed/predicted (O/E) mortality and morbidity ratios. New logistic regression equations for morbidity and mortality were then calculated using the scores from the POSSUM system and applied retrospectively. The O/E ratio for morbidity obtained from POSSUM score was 0.23. The O/E ratios for mortality from the POSSUM score and the P-POSSUM were 0.15 and 0.38, respectively. Utilizing the new equations using scores from the POSSUM, the O/E ratio increased to 0.88. Both the POSSUM and P-POSSUM over-predicted the morbidity and mortality in elective gastrointestinal surgery for malignant tumors in elderly patients. However, if a surgical unit makes appropriate calculations using its own patient series and updates these equations, the POSSUM system can be useful in the risk assessment for surgery in elderly patients.

Using High Resolution Model Data to Improve Lightning Forecasts across Southern California

NASA Astrophysics Data System (ADS)

Capps, S. B.; Rolinski, T.

2014-12-01

Dry lightning often results in a significant amount of fire starts in areas where the vegetation is dry and continuous. Meteorologists from the USDA Forest Service Predictive Services' program in Riverside, California are tasked to provide southern and central California's fire agencies with fire potential outlooks. Logistic regression equations were developed by these meteorologists several years ago, which forecast probabilities of lightning as well as lightning amounts, out to seven days across southern California. These regression equations were developed using ten years of historical gridded data from the Global Forecast System (GFS) model on a coarse scale (0.5 degree resolution), correlated with historical lightning strike data. These equations do a reasonably good job of capturing a lightning episode (3-5 consecutive days or greater of lightning), but perform poorly regarding more detailed information such as exact location and amounts. It is postulated that the inadequacies in resolving the finer details of episodic lightning events is due to the coarse resolution of the GFS data, along with limited predictors. Stability parameters, such as the Lifted Index (LI), the Total Totals index (TT), Convective Available Potential Energy (CAPE), along with Precipitable Water (PW) are the only parameters being considered as predictors. It is hypothesized that the statistical forecasts will benefit from higher resolution data both in training and implementing the statistical model. We have dynamically downscaled NCEP FNL (Final) reanalysis data using the Weather Research and Forecasting model (WRF) to 3km spatial and hourly temporal resolution across a decade. This dataset will be used to evaluate the contribution to the success of the statistical model of additional predictors in higher vertical, spatial and temporal resolution. If successful, we will implement an operational dynamically downscaled GFS forecast product to generate predictors for the resulting statistical lightning model. This data will help fire agencies be better prepared to pre-deploy resources in advance of these events. Specific information regarding duration, amount, and location will be especially valuable.

Age Estimation of Infants Through Metric Analysis of Developing Anterior Deciduous Teeth.

PubMed

Viciano, Joan; De Luca, Stefano; Irurita, Javier; Alemán, Inmaculada

2018-01-01

This study provides regression equations for estimation of age of infants from the dimensions of their developing deciduous teeth. The sample comprises 97 individuals of known sex and age (62 boys, 35 girls), aged between 2 days and 1,081 days. The age-estimation equations were obtained for the sexes combined, as well as for each sex separately, thus including "sex" as an independent variable. The values of the correlations and determination coefficients obtained for each regression equation indicate good fits for most of the equations obtained. The "sex" factor was statistically significant when included as an independent variable in seven of the regression equations. However, the "sex" factor provided an advantage for age estimation in only three of the equations, compared to those that did not include "sex" as a factor. These data suggest that the ages of infants can be accurately estimated from measurements of their developing deciduous teeth. © 2017 American Academy of Forensic Sciences.

Peak-flow characteristics of Virginia streams

USGS Publications Warehouse

Austin, Samuel H.; Krstolic, Jennifer L.; Wiegand, Ute

2011-01-01

Peak-flow annual exceedance probabilities, also called probability-percent chance flow estimates, and regional regression equations are provided describing the peak-flow characteristics of Virginia streams. Statistical methods are used to evaluate peak-flow data. Analysis of Virginia peak-flow data collected from 1895 through 2007 is summarized. Methods are provided for estimating unregulated peak flow of gaged and ungaged streams. Station peak-flow characteristics identified by fitting the logarithms of annual peak flows to a Log Pearson Type III frequency distribution yield annual exceedance probabilities of 0.5, 0.4292, 0.2, 0.1, 0.04, 0.02, 0.01, 0.005, and 0.002 for 476 streamgaging stations. Stream basin characteristics computed using spatial data and a geographic information system are used as explanatory variables in regional regression model equations for six physiographic regions to estimate regional annual exceedance probabilities at gaged and ungaged sites. Weighted peak-flow values that combine annual exceedance probabilities computed from gaging station data and from regional regression equations provide improved peak-flow estimates. Text, figures, and lists are provided summarizing selected peak-flow sites, delineated physiographic regions, peak-flow estimates, basin characteristics, regional regression model equations, error estimates, definitions, data sources, and candidate regression model equations. This study supersedes previous studies of peak flows in Virginia.

Separation in Logistic Regression: Causes, Consequences, and Control.

PubMed

Mansournia, Mohammad Ali; Geroldinger, Angelika; Greenland, Sander; Heinze, Georg

2018-04-01

Separation is encountered in regression models with a discrete outcome (such as logistic regression) where the covariates perfectly predict the outcome. It is most frequent under the same conditions that lead to small-sample and sparse-data bias, such as presence of a rare outcome, rare exposures, highly correlated covariates, or covariates with strong effects. In theory, separation will produce infinite estimates for some coefficients. In practice, however, separation may be unnoticed or mishandled because of software limits in recognizing and handling the problem and in notifying the user. We discuss causes of separation in logistic regression and describe how common software packages deal with it. We then describe methods that remove separation, focusing on the same penalized-likelihood techniques used to address more general sparse-data problems. These methods improve accuracy, avoid software problems, and allow interpretation as Bayesian analyses with weakly informative priors. We discuss likelihood penalties, including some that can be implemented easily with any software package, and their relative advantages and disadvantages. We provide an illustration of ideas and methods using data from a case-control study of contraceptive practices and urinary tract infection.

Modeling the dynamics of urban growth using multinomial logistic regression: a case study of Jiayu County, Hubei Province, China

NASA Astrophysics Data System (ADS)

Nong, Yu; Du, Qingyun; Wang, Kun; Miao, Lei; Zhang, Weiwei

2008-10-01

Urban growth modeling, one of the most important aspects of land use and land cover change study, has attracted substantial attention because it helps to comprehend the mechanisms of land use change thus helps relevant policies made. This study applied multinomial logistic regression to model urban growth in the Jiayu county of Hubei province, China to discover the relationship between urban growth and the driving forces of which biophysical and social-economic factors are selected as independent variables. This type of regression is similar to binary logistic regression, but it is more general because the dependent variable is not restricted to two categories, as those previous studies did. The multinomial one can simulate the process of multiple land use competition between urban land, bare land, cultivated land and orchard land. Taking the land use type of Urban as reference category, parameters could be estimated with odds ratio. A probability map is generated from the model to predict where urban growth will occur as a result of the computation.

Techniques for estimating peak-streamflow frequency for unregulated streams and streams regulated by small floodwater retarding structures in Oklahoma

USGS Publications Warehouse

Tortorelli, Robert L.

1997-01-01

Statewide regression equations for Oklahoma were determined for estimating peak discharge and flood frequency for selected recurrence intervals from 2 to 500 years for ungaged sites on natural unregulated streams. The most significant independent variables required to estimate peak-streamflow frequency for natural unregulated streams in Oklahoma are contributing drainage area, main-channel slope, and mean-annual precipitation. The regression equations are applicable for watersheds with drainage areas less than 2,510 square miles that are not affected by regulation from manmade works. Limitations on the use of the regression relations and the reliability of regression estimates for natural unregulated streams are discussed. Log-Pearson Type III analysis information, basin and climatic characteristics, and the peak-stream-flow frequency estimates for 251 gaging stations in Oklahoma and adjacent states are listed. Techniques are presented to make a peak-streamflow frequency estimate for gaged sites on natural unregulated streams and to use this result to estimate a nearby ungaged site on the same stream. For ungaged sites on urban streams, an adjustment of the statewide regression equations for natural unregulated streams can be used to estimate peak-streamflow frequency. For ungaged sites on streams regulated by small floodwater retarding structures, an adjustment of the statewide regression equations for natural unregulated streams can be used to estimate peak-streamflow frequency. The statewide regression equations are adjusted by substituting the drainage area below the floodwater retarding structures, or drainage area that represents the percentage of the unregulated basin, in the contributing drainage area parameter to obtain peak-streamflow frequency estimates.

The Bland-Altman Method Should Not Be Used in Regression Cross-Validation Studies

ERIC Educational Resources Information Center

O'Connor, Daniel P.; Mahar, Matthew T.; Laughlin, Mitzi S.; Jackson, Andrew S.

2011-01-01

The purpose of this study was to demonstrate the bias in the Bland-Altman (BA) limits of agreement method when it is used to validate regression models. Data from 1,158 men were used to develop three regression equations to estimate maximum oxygen uptake (R[superscript 2] = 0.40, 0.61, and 0.82, respectively). The equations were evaluated in a…

Data-driven discovery of partial differential equations.

PubMed

Rudy, Samuel H; Brunton, Steven L; Proctor, Joshua L; Kutz, J Nathan

2017-04-01

We propose a sparse regression method capable of discovering the governing partial differential equation(s) of a given system by time series measurements in the spatial domain. The regression framework relies on sparsity-promoting techniques to select the nonlinear and partial derivative terms of the governing equations that most accurately represent the data, bypassing a combinatorially large search through all possible candidate models. The method balances model complexity and regression accuracy by selecting a parsimonious model via Pareto analysis. Time series measurements can be made in an Eulerian framework, where the sensors are fixed spatially, or in a Lagrangian framework, where the sensors move with the dynamics. The method is computationally efficient, robust, and demonstrated to work on a variety of canonical problems spanning a number of scientific domains including Navier-Stokes, the quantum harmonic oscillator, and the diffusion equation. Moreover, the method is capable of disambiguating between potentially nonunique dynamical terms by using multiple time series taken with different initial data. Thus, for a traveling wave, the method can distinguish between a linear wave equation and the Korteweg-de Vries equation, for instance. The method provides a promising new technique for discovering governing equations and physical laws in parameterized spatiotemporal systems, where first-principles derivations are intractable.

Factors associated with developing a fear of falling in subjects with primary open-angle glaucoma.

PubMed

Adachi, Sayaka; Yuki, Kenya; Awano-Tanabe, Sachiko; Ono, Takeshi; Shiba, Daisuke; Murata, Hiroshi; Asaoka, Ryo; Tsubota, Kazuo

2018-02-13

To investigate the relationship between clinical risk factors, including visual field (VF) defects and visual acuity, and a fear of falling, among patients with primary open-angle glaucoma (POAG). All participants answered the following question at a baseline ophthalmic examination: Are you afraid of falling? The same question was then answered every 12 months for 3 years. A binocular integrated visual field was calculated by merging a patient's monocular Humphrey field analyzer VFs, using the 'best sensitivity' method. The means of total deviation values in the whole, superior peripheral, superior central, inferior central, and inferior peripheral VFs were calculated. The relationship between these mean VF measurements, and various clinical factors, against patients' baseline fear of falling and future fear of falling was analyzed using multiple logistic regression. Among 392 POAG subjects, 342 patients (87.2%) responded to the fear of falling question at least twice in the 3 years study period. The optimal regression model for patients' baseline fear of falling included age, gender, mean of total deviation values in the inferior peripheral VF and number of previous falls. The optimal regression equation for future fear of falling included age, gender, mean of total deviation values in the inferior peripheral VF and number of previous falls. Defects in the inferior peripheral VF area are significantly related to the development of a fear of falling.

General equations for optimal selection of diagnostic image acquisition parameters in clinical X-ray imaging.

PubMed

Zheng, Xiaoming

2017-12-01

The purpose of this work was to examine the effects of relationship functions between diagnostic image quality and radiation dose on the governing equations for image acquisition parameter variations in X-ray imaging. Various equations were derived for the optimal selection of peak kilovoltage (kVp) and exposure parameter (milliAmpere second, mAs) in computed tomography (CT), computed radiography (CR), and direct digital radiography. Logistic, logarithmic, and linear functions were employed to establish the relationship between radiation dose and diagnostic image quality. The radiation dose to the patient, as a function of image acquisition parameters (kVp, mAs) and patient size (d), was used in radiation dose and image quality optimization. Both logistic and logarithmic functions resulted in the same governing equation for optimal selection of image acquisition parameters using a dose efficiency index. For image quality as a linear function of radiation dose, the same governing equation was derived from the linear relationship. The general equations should be used in guiding clinical X-ray imaging through optimal selection of image acquisition parameters. The radiation dose to the patient could be reduced from current levels in medical X-ray imaging.

Logistic Mixed Models to Investigate Implicit and Explicit Belief Tracking.

PubMed

Lages, Martin; Scheel, Anne

2016-01-01

We investigated the proposition of a two-systems Theory of Mind in adults' belief tracking. A sample of N = 45 participants predicted the choice of one of two opponent players after observing several rounds in an animated card game. Three matches of this card game were played and initial gaze direction on target and subsequent choice predictions were recorded for each belief task and participant. We conducted logistic regressions with mixed effects on the binary data and developed Bayesian logistic mixed models to infer implicit and explicit mentalizing in true belief and false belief tasks. Although logistic regressions with mixed effects predicted the data well a Bayesian logistic mixed model with latent task- and subject-specific parameters gave a better account of the data. As expected explicit choice predictions suggested a clear understanding of true and false beliefs (TB/FB). Surprisingly, however, model parameters for initial gaze direction also indicated belief tracking. We discuss why task-specific parameters for initial gaze directions are different from choice predictions yet reflect second-order perspective taking.

Model selection for logistic regression models

NASA Astrophysics Data System (ADS)

Duller, Christine

2012-09-01

Model selection for logistic regression models decides which of some given potential regressors have an effect and hence should be included in the final model. The second interesting question is whether a certain factor is heterogeneous among some subsets, i.e. whether the model should include a random intercept or not. In this paper these questions will be answered with classical as well as with Bayesian methods. The application show some results of recent research projects in medicine and business administration.

Radiomorphometric analysis of frontal sinus for sex determination.

PubMed

Verma, Saumya; Mahima, V G; Patil, Karthikeya

2014-09-01

Sex determination of unknown individuals carries crucial significance in forensic research, in cases where fragments of skull persist with no likelihood of identification based on dental arch. In these instances sex determination becomes important to rule out certain number of possibilities instantly and helps in establishing a biological profile of human remains. The aim of the study is to evaluate a mathematical method based on logistic regression analysis capable of ascertaining the sex of individuals in the South Indian population. The study was conducted in the department of Oral Medicine and Radiology. The right and left areas, maximum height, width of frontal sinus were determined in 100 Caldwell views of 50 women and 50 men aged 20 years and above, with the help of Vernier callipers and a square grid with 1 square measuring 1mm(2) in area. Student's t-test, logistic regression analysis. The mean values of variables were greater in men, based on Student's t-test at 5% level of significance. The mathematical model based on logistic regression analysis gave percentage agreement of total area to correctly predict the female gender as 55.2%, of right area as 60.9% and of left area as 55.2%. The areas of the frontal sinus and the logistic regression proved to be unreliable in sex determination. (Logit = 0.924 - 0.00217 × right area).

Genetic prediction of type 2 diabetes using deep neural network.

PubMed

Kim, J; Kim, J; Kwak, M J; Bajaj, M

2018-04-01

Type 2 diabetes (T2DM) has strong heritability but genetic models to explain heritability have been challenging. We tested deep neural network (DNN) to predict T2DM using the nested case-control study of Nurses' Health Study (3326 females, 45.6% T2DM) and Health Professionals Follow-up Study (2502 males, 46.5% T2DM). We selected 96, 214, 399, and 678 single-nucleotide polymorphism (SNPs) through Fisher's exact test and L1-penalized logistic regression. We split each dataset randomly in 4:1 to train prediction models and test their performance. DNN and logistic regressions showed better area under the curve (AUC) of ROC curves than the clinical model when 399 or more SNPs included. DNN was superior than logistic regressions in AUC with 399 or more SNPs in male and 678 SNPs in female. Addition of clinical factors consistently increased AUC of DNN but failed to improve logistic regressions with 214 or more SNPs. In conclusion, we show that DNN can be a versatile tool to predict T2DM incorporating large numbers of SNPs and clinical information. Limitations include a relatively small number of the subjects mostly of European ethnicity. Further studies are warranted to confirm and improve performance of genetic prediction models using DNN in different ethnic groups. © 2017 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Unconditional or Conditional Logistic Regression Model for Age-Matched Case-Control Data?

PubMed

Kuo, Chia-Ling; Duan, Yinghui; Grady, James

2018-01-01

Matching on demographic variables is commonly used in case-control studies to adjust for confounding at the design stage. There is a presumption that matched data need to be analyzed by matched methods. Conditional logistic regression has become a standard for matched case-control data to tackle the sparse data problem. The sparse data problem, however, may not be a concern for loose-matching data when the matching between cases and controls is not unique, and one case can be matched to other controls without substantially changing the association. Data matched on a few demographic variables are clearly loose-matching data, and we hypothesize that unconditional logistic regression is a proper method to perform. To address the hypothesis, we compare unconditional and conditional logistic regression models by precision in estimates and hypothesis testing using simulated matched case-control data. Our results support our hypothesis; however, the unconditional model is not as robust as the conditional model to the matching distortion that the matching process not only makes cases and controls similar for matching variables but also for the exposure status. When the study design involves other complex features or the computational burden is high, matching in loose-matching data can be ignored for negligible loss in testing and estimation if the distributions of matching variables are not extremely different between cases and controls.

Unconditional or Conditional Logistic Regression Model for Age-Matched Case–Control Data?

PubMed Central

Kuo, Chia-Ling; Duan, Yinghui; Grady, James

2018-01-01

Matching on demographic variables is commonly used in case–control studies to adjust for confounding at the design stage. There is a presumption that matched data need to be analyzed by matched methods. Conditional logistic regression has become a standard for matched case–control data to tackle the sparse data problem. The sparse data problem, however, may not be a concern for loose-matching data when the matching between cases and controls is not unique, and one case can be matched to other controls without substantially changing the association. Data matched on a few demographic variables are clearly loose-matching data, and we hypothesize that unconditional logistic regression is a proper method to perform. To address the hypothesis, we compare unconditional and conditional logistic regression models by precision in estimates and hypothesis testing using simulated matched case–control data. Our results support our hypothesis; however, the unconditional model is not as robust as the conditional model to the matching distortion that the matching process not only makes cases and controls similar for matching variables but also for the exposure status. When the study design involves other complex features or the computational burden is high, matching in loose-matching data can be ignored for negligible loss in testing and estimation if the distributions of matching variables are not extremely different between cases and controls. PMID:29552553

Estimating multilevel logistic regression models when the number of clusters is low: a comparison of different statistical software procedures.

PubMed

Austin, Peter C

2010-04-22

Multilevel logistic regression models are increasingly being used to analyze clustered data in medical, public health, epidemiological, and educational research. Procedures for estimating the parameters of such models are available in many statistical software packages. There is currently little evidence on the minimum number of clusters necessary to reliably fit multilevel regression models. We conducted a Monte Carlo study to compare the performance of different statistical software procedures for estimating multilevel logistic regression models when the number of clusters was low. We examined procedures available in BUGS, HLM, R, SAS, and Stata. We found that there were qualitative differences in the performance of different software procedures for estimating multilevel logistic models when the number of clusters was low. Among the likelihood-based procedures, estimation methods based on adaptive Gauss-Hermite approximations to the likelihood (glmer in R and xtlogit in Stata) or adaptive Gaussian quadrature (Proc NLMIXED in SAS) tended to have superior performance for estimating variance components when the number of clusters was small, compared to software procedures based on penalized quasi-likelihood. However, only Bayesian estimation with BUGS allowed for accurate estimation of variance components when there were fewer than 10 clusters. For all statistical software procedures, estimation of variance components tended to be poor when there were only five subjects per cluster, regardless of the number of clusters.

Building a Decision Support System for Inpatient Admission Prediction With the Manchester Triage System and Administrative Check-in Variables.

PubMed

Zlotnik, Alexander; Alfaro, Miguel Cuchí; Pérez, María Carmen Pérez; Gallardo-Antolín, Ascensión; Martínez, Juan Manuel Montero

2016-05-01

The usage of decision support tools in emergency departments, based on predictive models, capable of estimating the probability of admission for patients in the emergency department may give nursing staff the possibility of allocating resources in advance. We present a methodology for developing and building one such system for a large specialized care hospital using a logistic regression and an artificial neural network model using nine routinely collected variables available right at the end of the triage process.A database of 255.668 triaged nonobstetric emergency department presentations from the Ramon y Cajal University Hospital of Madrid, from January 2011 to December 2012, was used to develop and test the models, with 66% of the data used for derivation and 34% for validation, with an ordered nonrandom partition. On the validation dataset areas under the receiver operating characteristic curve were 0.8568 (95% confidence interval, 0.8508-0.8583) for the logistic regression model and 0.8575 (95% confidence interval, 0.8540-0. 8610) for the artificial neural network model. χ Values for Hosmer-Lemeshow fixed "deciles of risk" were 65.32 for the logistic regression model and 17.28 for the artificial neural network model. A nomogram was generated upon the logistic regression model and an automated software decision support system with a Web interface was built based on the artificial neural network model.

Product unit neural network models for predicting the growth limits of Listeria monocytogenes.

PubMed

Valero, A; Hervás, C; García-Gimeno, R M; Zurera, G

2007-08-01

A new approach to predict the growth/no growth interface of Listeria monocytogenes as a function of storage temperature, pH, citric acid (CA) and ascorbic acid (AA) is presented. A linear logistic regression procedure was performed and a non-linear model was obtained by adding new variables by means of a Neural Network model based on Product Units (PUNN). The classification efficiency of the training data set and the generalization data of the new Logistic Regression PUNN model (LRPU) were compared with Linear Logistic Regression (LLR) and Polynomial Logistic Regression (PLR) models. 92% of the total cases from the LRPU model were correctly classified, an improvement on the percentage obtained using the PLR model (90%) and significantly higher than the results obtained with the LLR model, 80%. On the other hand predictions of LRPU were closer to data observed which permits to design proper formulations in minimally processed foods. This novel methodology can be applied to predictive microbiology for describing growth/no growth interface of food-borne microorganisms such as L. monocytogenes. The optimal balance is trying to find models with an acceptable interpretation capacity and with good ability to fit the data on the boundaries of variable range. The results obtained conclude that these kinds of models might well be very a valuable tool for mathematical modeling.

Analysis of a database to predict the result of allergy testing in vivo in patients with chronic nasal symptoms.

PubMed

Lacagnina, Valerio; Leto-Barone, Maria S; La Piana, Simona; Seidita, Aurelio; Pingitore, Giuseppe; Di Lorenzo, Gabriele

2014-01-01

This article uses the logistic regression model for diagnostic decision making in patients with chronic nasal symptoms. We studied the ability of the logistic regression model, obtained by the evaluation of a database, to detect patients with positive allergy skin-prick test (SPT) and patients with negative SPT. The model developed was validated using the data set obtained from another medical institution. The analysis was performed using a database obtained from a questionnaire administered to the patients with nasal symptoms containing personal data, clinical data, and results of allergy testing (SPT). All variables found to be significantly different between patients with positive and negative SPT (p < 0.05) were selected for the logistic regression models and were analyzed with backward stepwise logistic regression, evaluated with area under the curve of the receiver operating characteristic curve. A second set of patients from another institution was used to prove the model. The accuracy of the model in identifying, over the second set, both patients whose SPT will be positive and negative was high. The model detected 96% of patients with nasal symptoms and positive SPT and classified 94% of those with negative SPT. This study is preliminary to the creation of a software that could help the primary care doctors in a diagnostic decision making process (need of allergy testing) in patients complaining of chronic nasal symptoms.

Comparing machine learning and logistic regression methods for predicting hypertension using a combination of gene expression and next-generation sequencing data.

PubMed

Held, Elizabeth; Cape, Joshua; Tintle, Nathan

2016-01-01

Machine learning methods continue to show promise in the analysis of data from genetic association studies because of the high number of variables relative to the number of observations. However, few best practices exist for the application of these methods. We extend a recently proposed supervised machine learning approach for predicting disease risk by genotypes to be able to incorporate gene expression data and rare variants. We then apply 2 different versions of the approach (radial and linear support vector machines) to simulated data from Genetic Analysis Workshop 19 and compare performance to logistic regression. Method performance was not radically different across the 3 methods, although the linear support vector machine tended to show small gains in predictive ability relative to a radial support vector machine and logistic regression. Importantly, as the number of genes in the models was increased, even when those genes contained causal rare variants, model predictive ability showed a statistically significant decrease in performance for both the radial support vector machine and logistic regression. The linear support vector machine showed more robust performance to the inclusion of additional genes. Further work is needed to evaluate machine learning approaches on larger samples and to evaluate the relative improvement in model prediction from the incorporation of gene expression data.

Locally Weighted Score Estimation for Quantile Classification in Binary Regression Models

PubMed Central

Rice, John D.; Taylor, Jeremy M. G.

2016-01-01

One common use of binary response regression methods is classification based on an arbitrary probability threshold dictated by the particular application. Since this is given to us a priori, it is sensible to incorporate the threshold into our estimation procedure. Specifically, for the linear logistic model, we solve a set of locally weighted score equations, using a kernel-like weight function centered at the threshold. The bandwidth for the weight function is selected by cross validation of a novel hybrid loss function that combines classification error and a continuous measure of divergence between observed and fitted values; other possible cross-validation functions based on more common binary classification metrics are also examined. This work has much in common with robust estimation, but diers from previous approaches in this area in its focus on prediction, specifically classification into high- and low-risk groups. Simulation results are given showing the reduction in error rates that can be obtained with this method when compared with maximum likelihood estimation, especially under certain forms of model misspecification. Analysis of a melanoma data set is presented to illustrate the use of the method in practice. PMID:28018492

Methods for estimating magnitude and frequency of 1-, 3-, 7-, 15-, and 30-day flood-duration flows in Arizona

USGS Publications Warehouse

Kennedy, Jeffrey R.; Paretti, Nicholas V.; Veilleux, Andrea G.

2014-01-01

Regression equations, which allow predictions of n-day flood-duration flows for selected annual exceedance probabilities at ungaged sites, were developed using generalized least-squares regression and flood-duration flow frequency estimates at 56 streamgaging stations within a single, relatively uniform physiographic region in the central part of Arizona, between the Colorado Plateau and Basin and Range Province, called the Transition Zone. Drainage area explained most of the variation in the n-day flood-duration annual exceedance probabilities, but mean annual precipitation and mean elevation were also significant variables in the regression models. Standard error of prediction for the regression equations varies from 28 to 53 percent and generally decreases with increasing n-day duration. Outside the Transition Zone there are insufficient streamgaging stations to develop regression equations, but flood-duration flow frequency estimates are presented at select streamgaging stations.

Systolic time interval v heart rate regression equations using atropine: reproducibility studies.

PubMed Central

Kelman, A W; Sumner, D J; Whiting, B

1981-01-01

1. Systolic time intervals (STI) were recorded in six normal male subjects over a period of 3 weeks. On one day per week, each subject received incremental doses of atropine intravenously to increase heart rate, allowing the determination of individual STI v HR regression equations. On the other days STI were recorded with the subjects resting, in the supine position. 2. There were highly significant regression relationships between heart rate and both LVET and QS2, but not between heart rate and PEP. 3. The regression relationships showed little intra-subject variability, but a large degree of inter-subject variability: they proved adequate to correct the STI for the daily fluctuations in heart rate. 4. Administration of small doses of atropine intravenously provides a satisfactory and convenient method of deriving individual STI v HR regression equations which can be applied over a period of weeks. PMID:7248136

Systolic time interval v heart rate regression equations using atropine: reproducibility studies.

PubMed

Kelman, A W; Sumner, D J; Whiting, B

1981-07-01

1. Systolic time intervals (STI) were recorded in six normal male subjects over a period of 3 weeks. On one day per week, each subject received incremental doses of atropine intravenously to increase heart rate, allowing the determination of individual STI v HR regression equations. On the other days STI were recorded with the subjects resting, in the supine position. 2. There were highly significant regression relationships between heart rate and both LVET and QS2, but not between heart rate and PEP. 3. The regression relationships showed little intra-subject variability, but a large degree of inter-subject variability: they proved adequate to correct the STI for the daily fluctuations in heart rate. 4. Administration of small doses of atropine intravenously provides a satisfactory and convenient method of deriving individual STI v HR regression equations which can be applied over a period of weeks.

[Use of multiple regression models in observational studies (1970-2013) and requirements of the STROBE guidelines in Spanish scientific journals].

PubMed

Real, J; Cleries, R; Forné, C; Roso-Llorach, A; Martínez-Sánchez, J M

In medicine and biomedical research, statistical techniques like logistic, linear, Cox and Poisson regression are widely known. The main objective is to describe the evolution of multivariate techniques used in observational studies indexed in PubMed (1970-2013), and to check the requirements of the STROBE guidelines in the author guidelines in Spanish journals indexed in PubMed. A targeted PubMed search was performed to identify papers that used logistic linear Cox and Poisson models. Furthermore, a review was also made of the author guidelines of journals published in Spain and indexed in PubMed and Web of Science. Only 6.1% of the indexed manuscripts included a term related to multivariate analysis, increasing from 0.14% in 1980 to 12.3% in 2013. In 2013, 6.7, 2.5, 3.5, and 0.31% of the manuscripts contained terms related to logistic, linear, Cox and Poisson regression, respectively. On the other hand, 12.8% of journals author guidelines explicitly recommend to follow the STROBE guidelines, and 35.9% recommend the CONSORT guideline. A low percentage of Spanish scientific journals indexed in PubMed include the STROBE statement requirement in the author guidelines. Multivariate regression models in published observational studies such as logistic regression, linear, Cox and Poisson are increasingly used both at international level, as well as in journals published in Spanish. Copyright © 2015 Sociedad Española de Médicos de Atención Primaria (SEMERGEN). Publicado por Elsevier España, S.L.U. All rights reserved.

The microbiological profile and presence of bloodstream infection influence mortality rates in necrotizing fasciitis

PubMed Central

2011-01-01

Introduction Necrotizing fasciitis (NF) is a life threatening infectious disease with a high mortality rate. We carried out a microbiological characterization of the causative pathogens. We investigated the correlation of mortality in NF with bloodstream infection and with the presence of co-morbidities. Methods In this retrospective study, we analyzed 323 patients who presented with necrotizing fasciitis at two different institutions. Bloodstream infection (BSI) was defined as a positive blood culture result. The patients were categorized as survivors and non-survivors. Eleven clinically important variables which were statistically significant by univariate analysis were selected for multivariate regression analysis and a stepwise logistic regression model was developed to determine the association between BSI and mortality. Results Univariate logistic regression analysis showed that patients with hypotension, heart disease, liver disease, presence of Vibrio spp. in wound cultures, presence of fungus in wound cultures, and presence of Streptococcus group A, Aeromonas spp. or Vibrio spp. in blood cultures, had a significantly higher risk of in-hospital mortality. Our multivariate logistic regression analysis showed a higher risk of mortality in patients with pre-existing conditions like hypotension, heart disease, and liver disease. Multivariate logistic regression analysis also showed that presence of Vibrio spp in wound cultures, and presence of Streptococcus Group A in blood cultures were associated with a high risk of mortality while debridement > = 3 was associated with improved survival. Conclusions Mortality in patients with necrotizing fasciitis was significantly associated with the presence of Vibrio in wound cultures and Streptococcus group A in blood cultures. PMID:21693053

Prediction of siRNA potency using sparse logistic regression.

PubMed

Hu, Wei; Hu, John

2014-06-01

RNA interference (RNAi) can modulate gene expression at post-transcriptional as well as transcriptional levels. Short interfering RNA (siRNA) serves as a trigger for the RNAi gene inhibition mechanism, and therefore is a crucial intermediate step in RNAi. There have been extensive studies to identify the sequence characteristics of potent siRNAs. One such study built a linear model using LASSO (Least Absolute Shrinkage and Selection Operator) to measure the contribution of each siRNA sequence feature. This model is simple and interpretable, but it requires a large number of nonzero weights. We have introduced a novel technique, sparse logistic regression, to build a linear model using single-position specific nucleotide compositions which has the same prediction accuracy of the linear model based on LASSO. The weights in our new model share the same general trend as those in the previous model, but have only 25 nonzero weights out of a total 84 weights, a 54% reduction compared to the previous model. Contrary to the linear model based on LASSO, our model suggests that only a few positions are influential on the efficacy of the siRNA, which are the 5' and 3' ends and the seed region of siRNA sequences. We also employed sparse logistic regression to build a linear model using dual-position specific nucleotide compositions, a task LASSO is not able to accomplish well due to its high dimensional nature. Our results demonstrate the superiority of sparse logistic regression as a technique for both feature selection and regression over LASSO in the context of siRNA design.

Modeling of pathogen survival during simulated gastric digestion.

PubMed

Koseki, Shige; Mizuno, Yasuko; Sotome, Itaru

2011-02-01

The objective of the present study was to develop a mathematical model of pathogenic bacterial inactivation kinetics in a gastric environment in order to further understand a part of the infectious dose-response mechanism. The major bacterial pathogens Listeria monocytogenes, Escherichia coli O157:H7, and Salmonella spp. were examined by using simulated gastric fluid adjusted to various pH values. To correspond to the various pHs in a stomach during digestion, a modified logistic differential equation model and the Weibull differential equation model were examined. The specific inactivation rate for each pathogen was successfully described by a square-root model as a function of pH. The square-root models were combined with the modified logistic differential equation to obtain a complete inactivation curve. Both the modified logistic and Weibull models provided a highly accurate fitting of the static pH conditions for every pathogen. However, while the residuals plots of the modified logistic model indicated no systematic bias and/or regional prediction problems, the residuals plots of the Weibull model showed a systematic bias. The modified logistic model appropriately predicted the pathogen behavior in the simulated gastric digestion process with actual food, including cut lettuce, minced tuna, hamburger, and scrambled egg. Although the developed model enabled us to predict pathogen inactivation during gastric digestion, its results also suggested that the ingested bacteria in the stomach would barely be inactivated in the real digestion process. The results of this study will provide important information on a part of the dose-response mechanism of bacterial pathogens.

Modeling of Pathogen Survival during Simulated Gastric Digestion ▿

PubMed Central

Koseki, Shige; Mizuno, Yasuko; Sotome, Itaru

2011-01-01

The objective of the present study was to develop a mathematical model of pathogenic bacterial inactivation kinetics in a gastric environment in order to further understand a part of the infectious dose-response mechanism. The major bacterial pathogens Listeria monocytogenes, Escherichia coli O157:H7, and Salmonella spp. were examined by using simulated gastric fluid adjusted to various pH values. To correspond to the various pHs in a stomach during digestion, a modified logistic differential equation model and the Weibull differential equation model were examined. The specific inactivation rate for each pathogen was successfully described by a square-root model as a function of pH. The square-root models were combined with the modified logistic differential equation to obtain a complete inactivation curve. Both the modified logistic and Weibull models provided a highly accurate fitting of the static pH conditions for every pathogen. However, while the residuals plots of the modified logistic model indicated no systematic bias and/or regional prediction problems, the residuals plots of the Weibull model showed a systematic bias. The modified logistic model appropriately predicted the pathogen behavior in the simulated gastric digestion process with actual food, including cut lettuce, minced tuna, hamburger, and scrambled egg. Although the developed model enabled us to predict pathogen inactivation during gastric digestion, its results also suggested that the ingested bacteria in the stomach would barely be inactivated in the real digestion process. The results of this study will provide important information on a part of the dose-response mechanism of bacterial pathogens. PMID:21131530

In vitro differential diagnosis of clavus and verruca by a predictive model generated from electrical impedance.

PubMed

Hung, Chien-Ya; Sun, Pei-Lun; Chiang, Shu-Jen; Jaw, Fu-Shan

2014-01-01

Similar clinical appearances prevent accurate diagnosis of two common skin diseases, clavus and verruca. In this study, electrical impedance is employed as a novel tool to generate a predictive model for differentiating these two diseases. We used 29 clavus and 28 verruca lesions. To obtain impedance parameters, a LCR-meter system was applied to measure capacitance (C), resistance (Re), impedance magnitude (Z), and phase angle (θ). These values were combined with lesion thickness (d) to characterize the tissue specimens. The results from clavus and verruca were then fitted to a univariate logistic regression model with the generalized estimating equations (GEE) method. In model generation, log ZSD and θSD were formulated as predictors by fitting a multiple logistic regression model with the same GEE method. The potential nonlinear effects of covariates were detected by fitting generalized additive models (GAM). Moreover, the model was validated by the goodness-of-fit (GOF) assessments. Significant mean differences of the index d, Re, Z, and θ are found between clavus and verruca (p<0.001). A final predictive model is established with Z and θ indices. The model fits the observed data quite well. In GOF evaluation, the area under the receiver operating characteristics (ROC) curve is 0.875 (>0.7), the adjusted generalized R2 is 0.512 (>0.3), and the p value of the Hosmer-Lemeshow GOF test is 0.350 (>0.05). This technique promises to provide an approved model for differential diagnosis of clavus and verruca. It could provide a rapid, relatively low-cost, safe and non-invasive screening tool in clinic use.

The Prevalence and Incidence of Epiretinal Membranes in Eyes With Inactive Extramacular CMV Retinitis

PubMed Central

Kozak, Igor; Vaidya, Vijay; Van Natta, Mark L.; Pak, Jeong W.; May, K. Patrick; Thorne, Jennifer E.

2014-01-01

Purpose. To determine the prevalence and incidence of epiretinal membranes (ERM) in eyes with inactive extramacular cytomegalovirus (CMV) retinitis in patients with acquired immune deficiency syndrome (AIDS). Methods. A case–control report from a longitudinal multicenter observational study by the Studies of the Ocular Complications of AIDS (SOCA) Research Group. A total of 357 eyes of 270 patients with inactive CMV retinitis and 1084 eyes of 552 patients with no ocular opportunistic infection (OOI) were studied. Stereoscopic views of the posterior pole from fundus photographs were assessed at baseline and year 5 visits for the presence of macular ERM. Generalized estimating equations (GEE) logistic regression was used to compare the prevalence and 5-year incidence of ERM in eyes with and without CMV retinitis at enrollment. Crude and adjusted logistic regression was performed adjusting for possible confounders. Main outcome measures included the prevalence, incidence, estimated prevalence, and incidence odds ratios. Results. The prevalence of ERM at enrollment was 14.8% (53/357) in eyes with CMV retinitis versus 1.8% (19/1084) in eyes with no OOI. The incidence of ERM at 5 years was 18.6% (16/86) in eyes with CMV retinitis versus 2.4% (6/253) in eyes with no OOI. The crude odds ratio (OR) (95% confidence interval, CI) for prevalence was 9.8 (5.5–17.5) (P < 0.01). The crude OR (95% CI) for incidence was 9.4 (3.2–27.9) (P < 0.01). Conclusions. A history of extramacular CMV retinitis is associated with increased prevalence and incidence of ERM formation compared to what is seen in eyes without ocular opportunistic infections in AIDS patients. PMID:24925880

Association of different biomarkers of renal function with D-dimer levels in patients with type 1 diabetes mellitus (renal biomarkers and D-dimer in diabetes).

PubMed

Domingueti, Caroline Pereira; Fóscolo, Rodrigo Bastos; Dusse, Luci Maria S; Reis, Janice Sepúlveda; Carvalho, Maria das Graças; Gomes, Karina Braga; Fernandes, Ana Paula

2018-02-01

Objective This study aimed to evaluate the association between different renal biomarkers with D-Dimer levels in diabetes mellitus (DM1) patients group classified as: low D-Dimer levels (< 318 ng/mL), which included first and second D-Dimer tertiles, and high D-Dimer levels (≥ 318 ng/mL), which included third D-Dimer tertile. Materials and methods D-Dimer and cystatin C were measured by ELISA. Creatinine and urea were determined by enzymatic method. Estimated glomerular filtration rate (eGFR) was calculated using CKD-EPI equation. Albuminuria was assessed by immunoturbidimetry. Presence of renal disease was evaluated using each renal biomarker: creatinine, urea, cystatin C, eGFR and albuminuria. Bivariate logistic regression analysis was performed to assess which renal biomarkers are associated with high D-Dimer levels and odds ratio was calculated. After, multivariate logistic regression analysis was performed to assess which renal biomarkers are associated with high D-Dimer levels (after adjusting for sex and age) and odds ratio was calculated. Results Cystatin C presented a better association [OR of 9.8 (3.8-25.5)] with high D-Dimer levels than albuminuria, creatinine, eGFR and urea [OR of 5.3 (2.2-12.9), 8.4 (2.5-25.4), 9.1 (2.6-31.4) and 3.5 (1.4-8.4), respectively] after adjusting for sex and age. All biomarkers showed a good association with D-Dimer levels, and consequently, with hypercoagulability status, and cystatin C showed the best association among them. Conclusion Therefore, cystatin C might be useful to detect patients with incipient diabetic kidney disease that present an increased risk of cardiovascular disease, contributing to an early adoption of reno and cardioprotective therapies.

Personality, Driving Behavior and Mental Disorders Factors as Predictors of Road Traffic Accidents Based on Logistic Regression.

PubMed

Alavi, Seyyed Salman; Mohammadi, Mohammad Reza; Souri, Hamid; Mohammadi Kalhori, Soroush; Jannatifard, Fereshteh; Sepahbodi, Ghazal

2017-01-01

The aim of this study was to evaluate the effect of variables such as personality traits, driving behavior and mental illness on road traffic accidents among the drivers with accidents and those without road crash. In this cohort study, 800 bus and truck drivers were recruited. Participants were selected among drivers who referred to Imam Sajjad Hospital (Tehran, Iran) during 2013-2015. The Manchester driving behavior questionnaire (MDBQ), big five personality test (NEO personality inventory) and semi-structured interview (schizophrenia and affective disorders scale) were used. After two years, we surveyed all accidents due to human factors that involved the recruited drivers. The data were analyzed using the SPSS software by performing the descriptive statistics, t-test, and multiple logistic regression analysis methods. P values less than 0.05 were considered statistically significant. In terms of controlling the effective and demographic variables, the findings revealed significant differences between the two groups of drivers that were and were not involved in road accidents. In addition, it was found that depression and anxiety could increase the odds ratio (OR) of road accidents by 2.4- and 2.7-folds, respectively (P=0.04, P=0.004). It is noteworthy to mention that neuroticism alone can increase the odds of road accidents by 1.1-fold (P=0.009), but other personality factors did not have a significant effect on the equation. The results revealed that some mental disorders affect the incidence of road collisions. Considering the importance and sensitivity of driving behavior, it is necessary to evaluate multiple psychological factors influencing drivers before and after receiving or renewing their driver's license.

The prevalence and incidence of epiretinal membranes in eyes with inactive extramacular CMV retinitis.

PubMed

Kozak, Igor; Vaidya, Vijay; Van Natta, Mark L; Pak, Jeong W; May, K Patrick; Thorne, Jennifer E

2014-06-12

To determine the prevalence and incidence of epiretinal membranes (ERM) in eyes with inactive extramacular cytomegalovirus (CMV) retinitis in patients with acquired immune deficiency syndrome (AIDS). A case-control report from a longitudinal multicenter observational study by the Studies of the Ocular Complications of AIDS (SOCA) Research Group. A total of 357 eyes of 270 patients with inactive CMV retinitis and 1084 eyes of 552 patients with no ocular opportunistic infection (OOI) were studied. Stereoscopic views of the posterior pole from fundus photographs were assessed at baseline and year 5 visits for the presence of macular ERM. Generalized estimating equations (GEE) logistic regression was used to compare the prevalence and 5-year incidence of ERM in eyes with and without CMV retinitis at enrollment. Crude and adjusted logistic regression was performed adjusting for possible confounders. Main outcome measures included the prevalence, incidence, estimated prevalence, and incidence odds ratios. The prevalence of ERM at enrollment was 14.8% (53/357) in eyes with CMV retinitis versus 1.8% (19/1084) in eyes with no OOI. The incidence of ERM at 5 years was 18.6% (16/86) in eyes with CMV retinitis versus 2.4% (6/253) in eyes with no OOI. The crude odds ratio (OR) (95% confidence interval, CI) for prevalence was 9.8 (5.5-17.5) (P < 0.01). The crude OR (95% CI) for incidence was 9.4 (3.2-27.9) (P < 0.01). A history of extramacular CMV retinitis is associated with increased prevalence and incidence of ERM formation compared to what is seen in eyes without ocular opportunistic infections in AIDS patients. Copyright 2014 The Association for Research in Vision and Ophthalmology, Inc.

A prospective, observational cohort study of the seasonal dynamics of airway pathogens in the aetiology of exacerbations in COPD

PubMed Central

Wilkinson, Tom M A; Aris, Emmanuel; Bourne, Simon; Clarke, Stuart C; Peeters, Mathieu; Pascal, Thierry G; Schoonbroodt, Sonia; Tuck, Andrew C; Kim, Viktoriya; Williams, Nicholas; Williams, Anthony; Wootton, Stephen; Devaster, Jeanne-Marie

2017-01-01

Background The aetiology of acute exacerbations of COPD (AECOPD) is incompletely understood. Understanding the relationship between chronic bacterial airway infection and viral exposure may explain the incidence and seasonality of these events. Methods In this prospective, observational cohort study (NCT01360398), patients with COPD aged 40–85 years underwent sputum sampling monthly and at exacerbation for detection of bacteria and viruses. Results are presented for subjects in the full cohort, followed for 1 year. Interactions between exacerbation occurrence and pathogens were investigated by generalised estimating equation and stratified conditional logistic regression analyses. Findings The mean exacerbation rate per patient-year was 3.04 (95% CI 2.63 to 3.50). At AECOPD, the most common bacterial species were non-typeable Haemophilus influenzae (NTHi) and Moraxella catarrhalis, and the most common virus was rhinovirus. Logistic regression analyses (culture bacterial detection) showed significant OR for AECOPD occurrence when M. catarrhalis was detected regardless of season (5.09 (95% CI 2.76 to 9.41)). When NTHi was detected, the increased risk of exacerbation was greater in high season (October–March, OR 3.04 (1.80 to 5.13)) than low season (OR 1.22 (0.68 to 2.22)). Bacterial and viral coinfection was more frequent at exacerbation (24.9%) than stable state (8.6%). A significant interaction was detected between NTHi and rhinovirus presence and AECOPD risk (OR 5.18 (1.92 to 13.99); p=0.031). Conclusions AECOPD aetiology varies with season. Rises in incidence in winter may be driven by increased pathogen presence as well as an interaction between NTHi airway infection and effects of viral infection. Trial registration number Results, NCT01360398. PMID:28432209

Socio-Economic, Demographic and Lifestyle Determinants of Overweight and Obesity among Adults of Northeast India.

PubMed

Rengma, Melody Seb; Sen, Jaydip; Mondal, Nitish

2015-07-01

Overweight and obesity are the accumulation of high body adiposity, which can have detrimental health effects and contribute to the development of numerous preventable non-communicable diseases. This study aims to evaluate the effect of socio-economic, demographic and lifestyle factors on the prevalence of overweight and obesity among adults belonging to the Rengma-Naga population of North-east India. This cross-sectional study was conducted among 826 Rengma-Naga individuals (males: 422; females: 404) aged 20-49 years from the Karbi Anglong District of Assam, using a two-stage stratified random sampling. The socio-economic, demographic and lifestyle variables were recorded using structured schedules. Height and weight were recorded and the Body Mass Index (BMI) was calculated using standard procedures and equation. The WHO (2000) cut-off points were utilized to assess the prevalence of overweight (BMI ≥23.00-24.99 kg/m(2)) and obesity (BMI ≥25.00 kg/m(2)). The data were analysed using ANOVA, chi-square analysis and binary logistic regression analysis using SPSS (version 17.0). The prevalence of overweight and obesity were 32.57% (males: 39.34%; females: 25.50%) and 10.77% (males: 9.95%; females: 11.63%), respectively. The binary logistic regression analysis showed that age groups (e.g., 40-49 years), education (≥9(th) standard), part-time occupation and monthly income (≥Rs.10000) were significantly associated with overweight and obesity (p<0.05). Age, education occupation and income appear to have higher associations with overweight and obesity among adults. Suitable healthcare strategies and intervention programmes are needed for combating such prevalence in population.

Prevalence and risk factors for intimate partner violence among Grade 8 learners in urban South Africa: baseline analysis from the Skhokho Supporting Success cluster randomised controlled trial.

PubMed

Shamu, Simukai; Gevers, Anik; Mahlangu, B Pinky; Jama Shai, P Nwabisa; Chirwa, Esnat D; Jewkes, Rachel K

2016-01-01

Intimate partner violence (IPV) is a serious public health problem among adolescents. This study investigated the prevalence of and factors associated with Grade 8 girls' experience and boys' perpetration of IPV in South Africa. Participants were interviewed using interviewer-administered questionnaires about IPV, childhood violence, bullying, gender attitudes, alcohol use and risky sexual behaviours. Multiple logistic regression analysis was conducted to assess factors associated with girls' experience and boys' perpetration of IPV. Structural equation modelling (SEM) was conducted to assess the pathways to IPV experience and perpetration. Results show dating relationships are common among girls (52.5%) and boys (70.7%) and high prevalence of sexual or physical IPV experience by girls (30.9%; 95% CI: 28.2-33.7) and perpetration by boys (39.5%; 95% CI: 36.6-42.3). The logistic regression model showed factors associated with girls' experience of IPV include childhood experience of violence, individual gender inequitable attitudes, corporal punishment at home and in school, alcohol use, wider communication with one's partner and being more negative about school. We found three pathways from childhood trauma to IPV experience and perpetration in both models and these are through inequitable gender attitudes and risky sex, bullying and alcohol use. Prevention of IPV in children needs to encompass prevention of exposure to trauma in childhood and addressing gender attitudes and social norms to encourage positive disciplining approaches. : The trial is registered on ClinicalTrials.gov as NCT02349321. © The Author 2015. Published by Oxford University Press on behalf of Royal Society of Tropical Medicine and Hygiene. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Client-Related Factors Associated with a "Less than Good" Experience of Midwifery Care during Childbirth in the Netherlands.

PubMed

Baas, Carien I; Wiegers, Therese A; de Cock, T Paul; Erwich, Jan Jaap H M; Spelten, Evelien R; de Boer, Michiel R; Hutton, Eileen K

2017-03-01

A "less than good" experience during childbirth can affect a mother's early interaction with her child and may significantly influence a woman's emotional well-being. In this study, we focus on clients who experienced midwifery care provided during childbirth as "less than good" care. The aim of this study was to understand the relationship between client-related factors and the experience of midwifery care during childbirth to improve this care. This study was part of the "DELIVER study" where mothers report on the care they received. We used generalized estimation equations to control for correlations within midwife practices. Forward multivariate logistic regression analyses were conducted to model the client-related factors associated with the experienced midwifery care during childbirth. We included the responses of 2,377 women. In the multivariable logistic regression model, odds of reporting "less than good care" were significantly higher for women who experienced an unplanned cesarean birth (OR 2.21 [CI 1.19-4.09]), an instrumental birth (OR 1.55 [CI 1.08-2.23]), and less control during the dilation phase (OR 0.98 [CI 0.97-0.99]) and pushing phase (OR 0.98 [CI 0.97-0.99]). Birth-related factors were more likely than maternal characteristics to be associated with the experience of midwifery care during childbirth. We conclude that there is room for midwives to improve their care for women during childbirth particularly in improving the patient centeredness of the care provider, using strategies to enhance sense of control, and focusing on the particular needs of those who experience instrumental vaginal or unplanned cesarean births. © 2016 Wiley Periodicals, Inc.

Personality, Driving Behavior and Mental Disorders Factors as Predictors of Road Traffic Accidents Based on Logistic Regression

PubMed Central

Alavi, Seyyed Salman; Mohammadi, Mohammad Reza; Souri, Hamid; Mohammadi Kalhori, Soroush; Jannatifard, Fereshteh; Sepahbodi, Ghazal

2017-01-01

Background: The aim of this study was to evaluate the effect of variables such as personality traits, driving behavior and mental illness on road traffic accidents among the drivers with accidents and those without road crash. Methods: In this cohort study, 800 bus and truck drivers were recruited. Participants were selected among drivers who referred to Imam Sajjad Hospital (Tehran, Iran) during 2013-2015. The Manchester driving behavior questionnaire (MDBQ), big five personality test (NEO personality inventory) and semi-structured interview (schizophrenia and affective disorders scale) were used. After two years, we surveyed all accidents due to human factors that involved the recruited drivers. The data were analyzed using the SPSS software by performing the descriptive statistics, t-test, and multiple logistic regression analysis methods. P values less than 0.05 were considered statistically significant. Results: In terms of controlling the effective and demographic variables, the findings revealed significant differences between the two groups of drivers that were and were not involved in road accidents. In addition, it was found that depression and anxiety could increase the odds ratio (OR) of road accidents by 2.4- and 2.7-folds, respectively (P=0.04, P=0.004). It is noteworthy to mention that neuroticism alone can increase the odds of road accidents by 1.1-fold (P=0.009), but other personality factors did not have a significant effect on the equation. Conclusion: The results revealed that some mental disorders affect the incidence of road collisions. Considering the importance and sensitivity of driving behavior, it is necessary to evaluate multiple psychological factors influencing drivers before and after receiving or renewing their driver’s license. PMID:28293047

MAGI2 is an independent predictor of biochemical recurrence in prostate cancer.

PubMed

David, Stephanie N; Arnold Egloff, Shanna A; Goyal, Rajen; Clark, Peter E; Phillips, Sharon; Gellert, Lan L; Hameed, Omar; Giannico, Giovanna A

2018-06-01

Membrane-associated guanylate kinase, WW and PDZ domain-containing protein 2 (MAGI2) promotes the activity of phosphatase and tensin homolog (PTEN). Recent studies suggest that dysregulation of this signaling pathway has a role in prostate carcinogenesis. Our study aims to determine the prognostic significance of MAGI2 expression in prostate cancer. Tissue microarrays from 51 radical prostatectomy cases including benign prostatic tissue, high grade prostatic intraepithelial neoplasia (HGPIN), and adenocarcinoma were constructed. Immunohistochemistry with double staining for MAGI2 and p63 was performed and analyzed by image analysis as percent of analyzed area (%AREA). Multivariable logistic regression was used to correlate MAGI2 expression with clinical outcomes. Generalized Estimating Equations (GEE) with linear and logistic regression was used to correlate MAGI2 with intrapatient histology. MAGI2 %AREA was inversely associated with progression from HGPIN to adenocarcinoma of low to high Gleason score (OR, 0.980; slope, -0.02; P = 0.005) and HGPIN to cancer of any Gleason score (OR, 0.969; P = 0.007). After adjusting for grade, stage, and margin status, MAGI2 %AREA was a significant independent predictor of biochemical recurrence (BCR) (OR, 0.936; 95%CI, 0.880-0.996; P = 0.037; bootstrap P = 0.017). The addition of MAGI2 %AREA to these standard clinical parameters improved accuracy of predicting BCR by 2.9% (91.0% vs 88.1%). These results reveal that MAGI2 expression is reduced during prostate cancer progression and that retention of MAGI2 signal reduces odds of BCR. The study results further suggest a possible role of MAGI2 in prostate neoplasia. Decreased MAGI2 expression may help predict prostate cancer aggressiveness and provide new insight for treatment decisions and post-operative surveillance intervals. © 2018 Wiley Periodicals, Inc.

Change of sleep quality from pre- to 3 years post-solid organ transplantation: The Swiss Transplant Cohort Study

PubMed Central

Denhaerynck, Kris; Huynh-Do, Uyen; Binet, Isabelle; Hadaya, Karine; De Geest, Sabina

2017-01-01

Background Poor sleep quality (SQ) is common after solid organ transplantation; however, very little is known about its natural history. We assessed the changes in SQ from pre- to 3 years post-transplant in adult heart, kidney, liver and lung recipients included in the prospective nation-wide Swiss Transplant Cohort Study. We explored associations with selected variables in patients suffering persistent poor SQ compared to those with good or variable SQ. Methods Adult single organ transplant recipients enrolled in the Swiss Transplant Cohort Study with pre-transplant and at least 3 post-transplant SQ assessment data were included. SQ was self-reported pre-transplant (at listing), then at 6, 12, 24 and 36 months post-transplant. A single SQ item was used to identify poor (0–5) and good sleepers (6–10). Between organ groups, SQ was compared via logistic regression analysis with generalized estimating equations. Within the group reporting persistently poor SQ, we used logistic regression or Kaplan-Meier analysis as appropriate to check for differences in global quality of life and survival. Results In a sample of 1173 transplant patients (age: 52.1±13.2 years; 65% males; 66% kidney, 17% liver, 10% lung, 7% heart) transplanted between 2008 and 2012, pre- transplant poor SQ was highest in liver (50%) and heart (49%) recipients. Overall, poor SQ decreased significantly from pre-transplant (38%) to 24 months post-transplant (26%) and remained stable at 3 years (29%). Patients reporting persistently poor SQ had significantly more depressive symptomatology and lower global quality of life. Conclusion Because self-reported poor SQ is related to poorer global quality of life, these results emphasize the need for further studies to find suitable treatment options for poor SQ in transplant recipients. PMID:29020112

Obesity and socioeconomic disadvantage in midlife female public sector employees: a cohort study.

PubMed

Hiilamo, Aapo; Lallukka, Tea; Mänty, Minna; Kouvonen, Anne

2017-10-24

The two-way relationship between obesity and socioeconomic disadvantage is well established but previous studies on social and economic consequences of obesity have primarily focused on relatively young study populations. We examined whether obesity is associated with socioeconomic disadvantage through the 10-12-year follow-up, and how obesity-related socioeconomic inequalities develop during midlife among women. Baseline data were derived from the female population of the Helsinki Health Study cohort, comprising 40-60 -year-old employees of the City of Helsinki, Finland in 2000-2002 (n = 6913, response rate 69%). The follow-up surveys were carried out in 2007 (n = 5810) and 2012 (n = 5400). Socioeconomic disadvantage was measured by five dichotomous measures. Repeated logistic regression analyses utilising generalized estimating equations (GEE) were used to test the association between baseline self-reported obesity and the likelihood of socioeconomic disadvantage through all phases. The effect of time on the development of inequalities was examined by time interaction terms in random effect logistic regression models. After adjustment for educational level, baseline obesity was associated with repeated poverty (OR = 1.23; 95% CI; 1.05-1.44), frequent economic difficulties (OR = 1.74; 95% CI; 1.52-1.99), low household net income (OR = 1.23; 95% CI; 1.07-1.41), low household wealth (OR = 1.90; 95% CI; 1.59-2.26) and low personal income (OR = 1.22; 95% CI; 1.03-1.44). The differences in poverty rate and low personal income between the participants with obesity and participants with normal weight widened during the follow-up. Living without a partner and early exit from paid employment explained the widening of inequalities. Weight status inequalities in socioeconomic disadvantage persisted or widened during the late adulthood.

Which Patients Require Extended Thromboprophylaxis After Colectomy? Modeling Risk and Assessing Indications for Post-discharge Pharmacoprophylaxis.

PubMed

Beal, Eliza W; Tumin, Dmitry; Chakedis, Jeffery; Porter, Erica; Moris, Dimitrios; Zhang, Xu-Feng; Arnold, Mark; Harzman, Alan; Husain, Syed; Schmidt, Carl R; Pawlik, Timothy M

2018-07-01

Given the conflicting nature of reported risk factors for post-discharge venous thromboembolism (VTE) and unclear guidelines for post-discharge pharmacoprophylaxis, we sought to determine risk factors for 30-day post-discharge VTE after colectomy to predict which patients will benefit from post-discharge pharmacoprophylaxis. Patients who underwent colectomy in the American College of Surgeons National Surgical Quality Improvement Project Participant Use Files from 2011 to 2015 were identified. Logistic regression modeling was used. Receiver-operating characteristic curves were used and the best cut-points were determined using Youden's J index (sensitivity + specificity - 1). Hosmer-Lemeshow goodness-of-fit test was used to test model calibration. A random sample of 30% of the cohort was used as a validation set. Among 77,823 cases, the overall incidence of VTE after colectomy was 1.9%, with 0.7% of VTE events occurring in the post-discharge setting. Factors associated with post-discharge VTE risk including body mass index, preoperative albumin, operation time, hospital length of stay, race, smoking status, inflammatory bowel disease, return to the operating room and postoperative ileus were included in logistic regression equation model. The model demonstrated good calibration (goodness of fit P = 0.7137) and good discrimination (area under the curve (AUC) = 0.68; validation set, AUC = 0.70). A score of ≥-5.00 had the maxim sensitivity and specificity, resulting in 36.63% of patients being treated with prophylaxis for an overall VTE risk of 0.67%. Approximately one-third of post-colectomy VTE events occurred after discharge. Patients with predicted post-discharge VTE risk of ≥-5.00 should be recommended for extended post-discharge VTE prophylaxis.

Orthotopic bladder substitution in men revisited: identification of continence predictors.

PubMed

Koraitim, M M; Atta, M A; Foda, M K

2006-11-01

We determined the impact of the functional characteristics of the neobladder and urethral sphincter on continence results, and determined the most significant predictors of continence. A total of 88 male patients 29 to 70 years old underwent orthotopic bladder substitution with tubularized ileocecal segment (40) and detubularized sigmoid (25) or ileum (23). Uroflowmetry, cystometry and urethral pressure profilometry were performed at 13 to 36 months (mean 19) postoperatively. The correlation between urinary continence and 28 urodynamic variables was assessed. Parameters that correlated significantly with continence were entered into a multivariate analysis using a logistic regression model to determine the most significant predictors of continence. Maximum urethral closure pressure was the only parameter that showed a statistically significant correlation with diurnal continence. Nocturnal continence had not only a statistically significant positive correlation with maximum urethral closure pressure, but also statistically significant negative correlations with maximum contraction amplitude, and baseline pressure at mid and maximum capacity. Three of these 4 parameters, including maximum urethral closure pressure, maximum contraction amplitude and baseline pressure at mid capacity, proved to be significant predictors of continence on multivariate analysis. While daytime continence is determined by maximum urethral closure pressure, during the night it is the net result of 2 forces that have about equal influence but in opposite directions, that is maximum urethral closure pressure vs maximum contraction amplitude plus baseline pressure at mid capacity. Two equations were derived from the logistic regression model to predict the probability of continence after orthotopic bladder substitution, including Z1 (diurnal) = 0.605 + 0.0085 maximum urethral closure pressure and Z2 (nocturnal) = 0.841 + 0.01 [maximum urethral closure pressure - (maximum contraction amplitude + baseline pressure at mid capacity)].

Epilepsy, birth weight and academic school readiness in Canadian children: Data from the national longitudinal study of children and youth.

PubMed

Prasad, A N; Corbett, B

2017-02-01

Birth weight is an important indicator of prenatal/in-utero environment. Variations in birth weight have been reportedly associated with risks for cognitive problems. The National Longitudinal Survey of Children and Youth (NLSCY) dataset was explored to examine relationships between birth weight, academic school readiness and epilepsy. A population based sample of 32,900 children of the NLSCY were analyzed to examine associations between birth weight, and school readiness scores in 4-5-year-old children. Logistic and Linear regression was used to examine associations between having epilepsy and these outcomes. Gestation data was available on 19,867 children, full-term children represented 89.67% (gestation >259days), while 10.33% of children were premature (gestation <258days). There were 20 children with reported epilepsy in the sample. Effects of confounding variables (diabetes in pregnancy, smoking in pregnancy, high blood pressure during pregnancy, and gender of the infant) on birth weight and epilepsy were controlled using a separate structural equation model. Logistic regression analysis identified an association between epilepsy and lower birth weights, as well as an association between lower birth weight, having epilepsy and lower PPVT-R Scores. Model results show the relationship between low birth weight and epilepsy remains statistically significant even when controlling for the influence of afore mentioned confounding variables. Low birth weight appears to be associated with both epilepsy and academic school readiness. The data suggest that an abnormal prenatal environment can influence both childhood onset of epilepsy and cognition. Additional studies with larger sample sizes are needed to verify this relationship in detail. Copyright © 2017 Elsevier B.V. All rights reserved.

Weather adjustment using seemingly unrelated regression

DOE Office of Scientific and Technical Information (OSTI.GOV)

Noll, T.A.

1995-05-01

Seemingly unrelated regression (SUR) is a system estimation technique that accounts for time-contemporaneous correlation between individual equations within a system of equations. SUR is suited to weather adjustment estimations when the estimation is: (1) composed of a system of equations and (2) the system of equations represents either different weather stations, different sales sectors or a combination of different weather stations and different sales sectors. SUR utilizes the cross-equation error values to develop more accurate estimates of the system coefficients than are obtained using ordinary least-squares (OLS) estimation. SUR estimates can be generated using a variety of statistical software packagesmore » including MicroTSP and SAS.« less

Abdominal girth and vertebral column length aid in predicting intrathecal hyperbaric bupivacaine dose for elective cesarean section

PubMed Central

Wei, Chang-Na; Zhou, Qing-He; Wang, Li-Zhong

2017-01-01

Abstract Currently, there is no consensus on how to determine the optimal dose of intrathecal bupivacaine for an individual undergoing an elective cesarean section. In this study, we developed a regression equation between intrathecal 0.5% hyperbaric bupivacaine volume and abdominal girth and vertebral column length, to determine a suitable block level (T5) for elective cesarean section patients. In phase I, we analyzed 374 parturients undergoing an elective cesarean section that received a suitable dose of intrathecal 0.5% hyperbaric bupivacaine after a combined spinal-epidural (CSE) was performed at the L3/4 interspace. Parturients with T5 blockade to pinprick were selected for establishing the regression equation between 0.5% hyperbaric bupivacaine volume and vertebral column length and abdominal girth. Six parturient and neonatal variables, intrathecal 0.5% hyperbaric bupivacaine volume, and spinal anesthesia spread were recorded. Bivariate line correlation analyses, multiple line regression analyses, and 2-tailed t tests or chi-square test were performed, as appropriate. In phase II, another 200 parturients with CSE for elective cesarean section were enrolled to verify the accuracy of the regression equation. In phase I, a total of 143 parturients were selected to establish the following regression equation: YT5 = 0.074X1 − 0.022X2 − 0.017 (YT5 = 0.5% hyperbaric bupivacaine volume for T5 block level; X1 = vertebral column length; and X2 = abdominal girth). In phase II, a total of 189 participants were enrolled in the study to verify the accuracy of the regression equation, and 155 parturients with T5 blockade were deemed eligible, which accounted for 82.01% of all participants. This study evaluated parturients with T5 blockade to pinprick after a CSE for elective cesarean section to establish a regression equation between parturient vertebral column length and abdominal girth and 0.5% hyperbaric intrathecal bupivacaine volume. This equation can accurately predict the suitable intrathecal hyperbaric bupivacaine dose for elective cesarean section. PMID:28834913

Abdominal girth and vertebral column length aid in predicting intrathecal hyperbaric bupivacaine dose for elective cesarean section.

PubMed

Wei, Chang-Na; Zhou, Qing-He; Wang, Li-Zhong

2017-08-01

Currently, there is no consensus on how to determine the optimal dose of intrathecal bupivacaine for an individual undergoing an elective cesarean section. In this study, we developed a regression equation between intrathecal 0.5% hyperbaric bupivacaine volume and abdominal girth and vertebral column length, to determine a suitable block level (T5) for elective cesarean section patients.In phase I, we analyzed 374 parturients undergoing an elective cesarean section that received a suitable dose of intrathecal 0.5% hyperbaric bupivacaine after a combined spinal-epidural (CSE) was performed at the L3/4 interspace. Parturients with T5 blockade to pinprick were selected for establishing the regression equation between 0.5% hyperbaric bupivacaine volume and vertebral column length and abdominal girth. Six parturient and neonatal variables, intrathecal 0.5% hyperbaric bupivacaine volume, and spinal anesthesia spread were recorded. Bivariate line correlation analyses, multiple line regression analyses, and 2-tailed t tests or chi-square test were performed, as appropriate. In phase II, another 200 parturients with CSE for elective cesarean section were enrolled to verify the accuracy of the regression equation.In phase I, a total of 143 parturients were selected to establish the following regression equation: YT5 = 0.074X1 - 0.022X2 - 0.017 (YT5 = 0.5% hyperbaric bupivacaine volume for T5 block level; X1 = vertebral column length; and X2 = abdominal girth). In phase II, a total of 189 participants were enrolled in the study to verify the accuracy of the regression equation, and 155 parturients with T5 blockade were deemed eligible, which accounted for 82.01% of all participants.This study evaluated parturients with T5 blockade to pinprick after a CSE for elective cesarean section to establish a regression equation between parturient vertebral column length and abdominal girth and 0.5% hyperbaric intrathecal bupivacaine volume. This equation can accurately predict the suitable intrathecal hyperbaric bupivacaine dose for elective cesarean section.

Combining logistic regression with classification and regression tree to predict quality of care in a home health nursing data set.

PubMed

Guo, Huey-Ming; Shyu, Yea-Ing Lotus; Chang, Her-Kun

2006-01-01

In this article, the authors provide an overview of a research method to predict quality of care in home health nursing data set. The results of this study can be visualized through classification an regression tree (CART) graphs. The analysis was more effective, and the results were more informative since the home health nursing dataset was analyzed with a combination of the logistic regression and CART, these two techniques complete each other. And the results more informative that more patients' characters were related to quality of care in home care. The results contributed to home health nurse predict patient outcome in case management. Improved prediction is needed for interventions to be appropriately targeted for improved patient outcome and quality of care.

Rural-to-Urban Migration: Socioeconomic Status But Not Acculturation was Associated with Overweight/Obesity Risk.

PubMed

Hilmers, Angela; Bernabé-Ortiz, Antonio; Gilman, Robert H; McDermott, Ann Y; Smeeth, Liam; Miranda, J Jaime

2016-06-01

To investigate whether socioeconomic status (SES) and acculturation predict overweight/obesity risk as well as the mediating effect of physical activity (PA) in the context of internal migration. Cross-sectional study of 587 rural-to-urban migrants participating in the PERU MIGRANT study. Analyses were conducted using logistic regression and structured equation modeling. Interaction effects of SES and acculturation were tested. Models were controlled for age, gender and education. Only SES was a significant predictor of overweight/obesity risk. Lower SES decreased the odds of being overweight/obese by 51.4 %. This association did not vary by gender nor was it explained by PA. Mechanisms underlying the relationship between SES and overweight/obesity may differ depending on the geographic location and sociocultural context of the population studied. Research on internal migration and health would benefit from the development of tailored acculturation measures and the evaluation of exploratory models that include diet.

Quantifying risk and assessing outcome in cardiac surgery.

PubMed

Higgins, T L

1998-06-01

Quality improvement, research, and reporting of outcome results can be stratified by preoperative risk by using a logistic regression equation or scores to correct for multiple risk factors. The more than 30-fold mortality differences between lowest and highest risk patients make it critical to stratify outcome results by patient severity. Probabilities are not predictions, however, and caution must be exercised when applying scores to individuals. Outcome assessment will grow in its importance to professionals, initially in the guise of quality reporting and improvement, but increasingly as a tool for risk assessment, patient counseling, and directing therapeutic decisions based on more complete information about patient subgroups. Physicians may be called on for recommendations in choosing systems for their hospitals and communities. Therefore, it is important to have an understanding of how such systems are developed, what factors indicate adequate performance of a system, and how such systems of risk stratification should be applied in practice.

Adult attachment style and childhood interpersonal trauma in non-epileptic attack disorder.

PubMed

Holman, Natalie; Kirkby, Antonia; Duncan, Susan; Brown, Richard J

2008-03-01

Non-epileptic attack disorder (NEAD) poses a significant clinical problem but is poorly understood. Attachment theory provides a framework for understanding the development and maintenance of NEAD and the contribution of childhood abuse and neglect to these processes. A cross-sectional design was used to study attachment style and early traumatic experiences in individuals with NEAD (N=17) compared to those with epilepsy (N=26). A significant difference in predominant attachment style between the two groups was found, with fearful attachment occurring more frequently in the NEAD group. Abuse and neglect were also significantly more common in the NEAD patients. Both early traumatic experiences and fearful attachment added significantly to the predictive power of a logistic regression equation after controlling for anxiety and dysthymia. The findings suggest a link between disturbed attachment and NEAD and have clinical implications for therapeutic intervention with this group.

A short generic measure of work stress in the era of globalization: effort-reward imbalance.

PubMed

Siegrist, Johannes; Wege, Natalia; Pühlhofer, Frank; Wahrendorf, Morten

2009-08-01

We evaluate psychometric properties of a short version of the original effort-reward imbalance (ERI) questionnaire. This measure is of interest in the context of assessing stressful work conditions in the era of economic globalization. In a representative sample of 10,698 employed men and women participating in the longitudinal Socio-Economic Panel (SOEP) in Germany, a short version of the ERI questionnaire was included in the 2006 panel wave. Structural equation modeling and logistic regression analysis were applied. In addition to satisfactory internal consistency of scales, a model representing the theoretical structure of the scales provided the best data fit in a competitive test (RMSEA = 0.059, CAIC = 4124.19). Scoring high on the ERI scales was associated with elevated risks of poor self-rated health. This short version of the ERI questionnaire reveals satisfactory psychometric properties, and can be recommended for further use in research and practice.

Prediction and stability of reading problems in middle childhood.

PubMed

Ritchey, Kristen D; Silverman, Rebecca D; Schatschneider, Christopher; Speece, Deborah L

2015-01-01

The longitudinal prediction of reading problems from fourth grade to sixth grade was investigated with a sample of 173 students. Reading problems at the end of sixth grade were defined by significantly below average performance (≤ 15th percentile) on reading factors defining word reading, fluency, and reading comprehension. Sixth grade poor reader status was predicted by fall of fourth grade passage reading fluency, spelling fluency, and the number of reading problems identified by teachers. Reading fluency and spelling fluency were significant predictors in logistic regression equation that combined to yield a screening battery with an area under the curve of .91. These results suggest that brief assessments of reading and spelling fluency in fourth grade may be able to identify students in middle childhood who have a reading problem or who are at risk for experiencing reading problems in sixth grade. © Hammill Institute on Disabilities 2013.

Word recognition materials for native speakers of Taiwan Mandarin.

PubMed

Nissen, Shawn L; Harris, Richard W; Dukes, Alycia

2008-06-01

To select, digitally record, evaluate, and psychometrically equate word recognition materials that can be used to measure the speech perception abilities of native speakers of Taiwan Mandarin in quiet. Frequently used bisyllabic words produced by male and female talkers of Taiwan Mandarin were digitally recorded and subsequently evaluated using 20 native listeners with normal hearing at 10 intensity levels (-5 to 40 dB HL) in increments of 5 dB. Using logistic regression, 200 words with the steepest psychometric slopes were divided into 4 lists and 8 half-lists that were relatively equivalent in psychometric function slope. To increase auditory homogeneity of the lists, the intensity of words in each list was digitally adjusted so that the threshold of each list was equal to the midpoint between the mean thresholds of the male and female half-lists. Digital recordings of the word recognition lists and the associated clinical instructions are available on CD upon request.

The building blocks of a 'Liveable Neighbourhood': Identifying the key performance indicators for walking of an operational planning policy in Perth, Western Australia.

PubMed

Hooper, Paula; Knuiman, Matthew; Foster, Sarah; Giles-Corti, Billie

2015-11-01

Planning policy makers are requesting clearer guidance on the key design features required to build neighbourhoods that promote active living. Using a backwards stepwise elimination procedure (logistic regression with generalised estimating equations adjusting for demographic characteristics, self-selection factors, stage of construction and scale of development) this study identified specific design features (n=16) from an operational planning policy ("Liveable Neighbourhoods") that showed the strongest associations with walking behaviours (measured using the Neighbourhood Physical Activity Questionnaire). The interacting effects of design features on walking behaviours were also investigated. The urban design features identified were grouped into the "building blocks of a Liveable Neighbourhood", reflecting the scale, importance and sequencing of the design and implementation phases required to create walkable, pedestrian friendly developments. Copyright © 2015 Elsevier Ltd. All rights reserved.

A general framework for the use of logistic regression models in meta-analysis.

PubMed

Simmonds, Mark C; Higgins, Julian Pt

2016-12-01

Where individual participant data are available for every randomised trial in a meta-analysis of dichotomous event outcomes, "one-stage" random-effects logistic regression models have been proposed as a way to analyse these data. Such models can also be used even when individual participant data are not available and we have only summary contingency table data. One benefit of this one-stage regression model over conventional meta-analysis methods is that it maximises the correct binomial likelihood for the data and so does not require the common assumption that effect estimates are normally distributed. A second benefit of using this model is that it may be applied, with only minor modification, in a range of meta-analytic scenarios, including meta-regression, network meta-analyses and meta-analyses of diagnostic test accuracy. This single model can potentially replace the variety of often complex methods used in these areas. This paper considers, with a range of meta-analysis examples, how random-effects logistic regression models may be used in a number of different types of meta-analyses. This one-stage approach is compared with widely used meta-analysis methods including Bayesian network meta-analysis and the bivariate and hierarchical summary receiver operating characteristic (ROC) models for meta-analyses of diagnostic test accuracy. © The Author(s) 2014.

Asthma exacerbation and proximity of residence to major roads: a population-based matched case-control study among the pediatric Medicaid population in Detroit, Michigan

PubMed Central

2011-01-01

Background The relationship between asthma and traffic-related pollutants has received considerable attention. The use of individual-level exposure measures, such as residence location or proximity to emission sources, may avoid ecological biases. Method This study focused on the pediatric Medicaid population in Detroit, MI, a high-risk population for asthma-related events. A population-based matched case-control analysis was used to investigate associations between acute asthma outcomes and proximity of residence to major roads, including freeways. Asthma cases were identified as all children who made at least one asthma claim, including inpatient and emergency department visits, during the three-year study period, 2004-06. Individually matched controls were randomly selected from the rest of the Medicaid population on the basis of non-respiratory related illness. We used conditional logistic regression with distance as both categorical and continuous variables, and examined non-linear relationships with distance using polynomial splines. The conditional logistic regression models were then extended by considering multiple asthma states (based on the frequency of acute asthma outcomes) using polychotomous conditional logistic regression. Results Asthma events were associated with proximity to primary roads with an odds ratio of 0.97 (95% CI: 0.94, 0.99) for a 1 km increase in distance using conditional logistic regression, implying that asthma events are less likely as the distance between the residence and a primary road increases. Similar relationships and effect sizes were found using polychotomous conditional logistic regression. Another plausible exposure metric, a reduced form response surface model that represents atmospheric dispersion of pollutants from roads, was not associated under that exposure model. Conclusions There is moderately strong evidence of elevated risk of asthma close to major roads based on the results obtained in this population-based matched case-control study. PMID:21513554

Neural network modeling for surgical decisions on traumatic brain injury patients.

PubMed

Li, Y C; Liu, L; Chiu, W T; Jian, W S

2000-01-01

Computerized medical decision support systems have been a major research topic in recent years. Intelligent computer programs were implemented to aid physicians and other medical professionals in making difficult medical decisions. This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS). These models were developed based on a large TBI patient database. This MDSS accepts a set of patient data such as the types of skull fracture, Glasgow Coma Scale (GCS), episode of convulsion and return the chance that a neurosurgeon would recommend an open-skull surgery for this patient. The three mathematical models described in this report including a logistic regression model, a multi-layer perceptron (MLP) neural network and a radial-basis-function (RBF) neural network. From the 12,640 patients selected from the database. A randomly drawn 9480 cases were used as the training group to develop/train our models. The other 3160 cases were in the validation group which we used to evaluate the performance of these models. We used sensitivity, specificity, areas under receiver-operating characteristics (ROC) curve and calibration curves as the indicator of how accurate these models are in predicting a neurosurgeon's decision on open-skull surgery. The results showed that, assuming equal importance of sensitivity and specificity, the logistic regression model had a (sensitivity, specificity) of (73%, 68%), compared to (80%, 80%) from the RBF model and (88%, 80%) from the MLP model. The resultant areas under ROC curve for logistic regression, RBF and MLP neural networks are 0.761, 0.880 and 0.897, respectively (P < 0.05). Among these models, the logistic regression has noticeably poorer calibration. This study demonstrated the feasibility of applying neural networks as the mechanism for TBI decision support systems based on clinical databases. The results also suggest that neural networks may be a better solution for complex, non-linear medical decision support systems than conventional statistical techniques such as logistic regression.

Cluster Analysis of Campylobacter jejuni Genotypes Isolated from Small and Medium-Sized Mammalian Wildlife and Bovine Livestock from Ontario Farms.

PubMed

Viswanathan, M; Pearl, D L; Taboada, E N; Parmley, E J; Mutschall, S K; Jardine, C M

2017-05-01

Using data collected from a cross-sectional study of 25 farms (eight beef, eight swine and nine dairy) in 2010, we assessed clustering of molecular subtypes of C. jejuni based on a Campylobacter-specific 40 gene comparative genomic fingerprinting assay (CGF40) subtypes, using unweighted pair-group method with arithmetic mean (UPGMA) analysis, and multiple correspondence analysis. Exact logistic regression was used to determine which genes differentiate wildlife and livestock subtypes in our study population. A total of 33 bovine livestock (17 beef and 16 dairy), 26 wildlife (20 raccoon (Procyon lotor), five skunk (Mephitis mephitis) and one mouse (Peromyscus spp.) C. jejuni isolates were subtyped using CGF40. Dendrogram analysis, based on UPGMA, showed distinct branches separating bovine livestock and mammalian wildlife isolates. Furthermore, two-dimensional multiple correspondence analysis was highly concordant with dendrogram analysis showing clear differentiation between livestock and wildlife CGF40 subtypes. Based on multilevel logistic regression models with a random intercept for farm of origin, we found that isolates in general, and raccoons more specifically, were significantly more likely to be part of the wildlife branch. Exact logistic regression conducted gene by gene revealed 15 genes that were predictive of whether an isolate was of wildlife or bovine livestock isolate origin. Both multiple correspondence analysis and exact logistic regression revealed that in most cases, the presence of a particular gene (13 of 15) was associated with an isolate being of livestock rather than wildlife origin. In conclusion, the evidence gained from dendrogram analysis, multiple correspondence analysis and exact logistic regression indicates that mammalian wildlife carry CGF40 subtypes of C. jejuni distinct from those carried by bovine livestock. Future studies focused on source attribution of C. jejuni in human infections will help determine whether wildlife transmit Campylobacter jejuni directly to humans. © 2016 Blackwell Verlag GmbH.

Wind tunnel test of Teledyne Geotech model 1564B cup anemometer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Parker, M.J.; Addis, R.P.

1991-04-04

The Department of Energy (DOE) Environment, Safety and Health Compliance Assessment (Tiger Team) of the Savannah River Site (SRS) questioned the method by which wind speed sensors (cup anemometers) are calibrated by the Environmental Technology Section (ETS). The Tiger Team member was concerned that calibration data was generated by running the wind tunnel to only 26 miles per hour (mph) when speeds exceeding 50 mph are readily obtainable. A wind tunnel experiment was conducted and confirmed the validity of the practice. Wind speeds common to SRS (6 mph) were predicted more accurately by 0--25 mph regression equations than 0--50 mphmore » regression equations. Higher wind speeds were slightly overpredicted by the 0--25 mph regression equations when compared to 0--50 mph regression equations. However, the greater benefit of more accurate lower wind speed predictions accuracy outweight the benefit of slightly better high (extreme) wind speed predictions. Therefore, it is concluded that 0--25 mph regression equations should continue to be utilized by ETS at SRS. During the Department of Energy Tiger Team audit, concerns were raised about the calibration of SRS cup anemometers. Wind speed is measured by ETS with Teledyne Geotech model 1564B cup anemometers, which are calibrated in the ETS wind tunnel. Linear regression lines are fitted to data points of tunnel speed versus anemometer output voltages up to 25 mph. The regression coefficients are then implemented into the data acquisition computer software when an instrument is installed in the field. The concern raised was that since the wind tunnel at SRS is able to generate a maximum wind speed higher than 25 mph, errors may be introduced in not using the full range of the wind tunnel.« less

Wind tunnel test of Teledyne Geotech model 1564B cup anemometer

NASA Astrophysics Data System (ADS)

Parker, M. J.; Addis, R. P.

1991-04-01

The Department of Energy (DOE) Environment, Safety, and Health Compliance Assessment (Tiger Team) of the Savannah River Site (SRS) questioned the method by which wind speed sensors (cup anemometers) are calibrated by the Environmental Technology Section (ETS). The Tiger Team member was concerned that calibration data was generated by running the wind tunnel to only 26 miles per hour (mph) when speeds exceeding 50 mph are readily obtainable. A wind tunnel experiment was conducted and confirmed the validity of the practice. Wind speeds common to SRS (6 mph) were predicted more accurately by 0-25 mph regression equations than 0-50 mph regression equations. Higher wind speeds were slightly overpredicted by the 0-25 mph regression equations when compared to 0-50 mph regression equations. However, the greater benefit of more accurate lower wind speed predictions accuracy outweigh the benefit of slightly better high (extreme) wind speed predictions. Therefore, it is concluded that 0-25 mph regression equations should continue to be utilized by ETS at SRS. During the Department of Energy Tiger Team audit, concerns were raised about the calibration of SRS cup anemometers. Wind speed is measured by ETS with Teledyne Geotech model 1564B cup anemometers, which are calibrated in the ETS wind tunnel. Linear regression lines are fitted to data points of tunnel speed versus anemometer output voltages up to 25 mph. The regression coefficients are then implemented into the data acquisition computer software when an instrument is installed in the field. The concern raised was that since the wind tunnel at SRS is able to generate a maximum wind speed higher than 25 mph, errors may be introduced in not using the full range of the wind tunnel.

Evaluation of the magnitude and frequency of floods in urban watersheds in Phoenix and Tucson, Arizona

USGS Publications Warehouse

Kennedy, Jeffrey R.; Paretti, Nicholas V.

2014-01-01

Flooding in urban areas routinely causes severe damage to property and often results in loss of life. To investigate the effect of urbanization on the magnitude and frequency of flood peaks, a flood frequency analysis was carried out using data from urbanized streamgaging stations in Phoenix and Tucson, Arizona. Flood peaks at each station were predicted using the log-Pearson Type III distribution, fitted using the expected moments algorithm and the multiple Grubbs-Beck low outlier test. The station estimates were then compared to flood peaks estimated by rural-regression equations for Arizona, and to flood peaks adjusted for urbanization using a previously developed procedure for adjusting U.S. Geological Survey rural regression peak discharges in an urban setting. Only smaller, more common flood peaks at the 50-, 20-, 10-, and 4-percent annual exceedance probabilities (AEPs) demonstrate any increase in magnitude as a result of urbanization; the 1-, 0.5-, and 0.2-percent AEP flood estimates are predicted without bias by the rural-regression equations. Percent imperviousness was determined not to account for the difference in estimated flood peaks between stations, either when adjusting the rural-regression equations or when deriving urban-regression equations to predict flood peaks directly from basin characteristics. Comparison with urban adjustment equations indicates that flood peaks are systematically overestimated if the rural-regression-estimated flood peaks are adjusted upward to account for urbanization. At nearly every streamgaging station in the analysis, adjusted rural-regression estimates were greater than the estimates derived using station data. One likely reason for the lack of increase in flood peaks with urbanization is the presence of significant stormwater retention and detention structures within the watershed used in the study.

2012 Workplace and Gender Relations Survey of Reserve Component Members: Statistical Methodology Report

DTIC Science & Technology

2012-09-01

3,435 10,461 9.1 3.1 63 Unmarried with Children+ Unmarried without Children 439,495 0.01 10,350 43,870 10.1 2.2 64 Married with Children+ Married ...logistic regression model was used to predict the probability of eligibility for the survey (known eligibility vs . unknown eligibility). A second logistic...regression model was used to predict the probability of response among eligible sample members (complete response vs . non-response). CHAID (Chi

Habitat features and predictive habitat modeling for the Colorado chipmunk in southern New Mexico

USGS Publications Warehouse

Rivieccio, M.; Thompson, B.C.; Gould, W.R.; Boykin, K.G.

2003-01-01

Two subspecies of Colorado chipmunk (state threatened and federal species of concern) occur in southern New Mexico: Tamias quadrivittatus australis in the Organ Mountains and T. q. oscuraensis in the Oscura Mountains. We developed a GIS model of potentially suitable habitat based on vegetation and elevation features, evaluated site classifications of the GIS model, and determined vegetation and terrain features associated with chipmunk occurrence. We compared GIS model classifications with actual vegetation and elevation features measured at 37 sites. At 60 sites we measured 18 habitat variables regarding slope, aspect, tree species, shrub species, and ground cover. We used logistic regression to analyze habitat variables associated with chipmunk presence/absence. All (100%) 37 sample sites (28 predicted suitable, 9 predicted unsuitable) were classified correctly by the GIS model regarding elevation and vegetation. For 28 sites predicted suitable by the GIS model, 18 sites (64%) appeared visually suitable based on habitat variables selected from logistic regression analyses, of which 10 sites (36%) were specifically predicted as suitable habitat via logistic regression. We detected chipmunks at 70% of sites deemed suitable via the logistic regression models. Shrub cover, tree density, plant proximity, presence of logs, and presence of rock outcrop were retained in the logistic model for the Oscura Mountains; litter, shrub cover, and grass cover were retained in the logistic model for the Organ Mountains. Evaluation of predictive models illustrates the need for multi-stage analyses to best judge performance. Microhabitat analyses indicate prospective needs for different management strategies between the subspecies. Sensitivities of each population of the Colorado chipmunk to natural and prescribed fire suggest that partial burnings of areas inhabited by Colorado chipmunks in southern New Mexico may be beneficial. These partial burnings may later help avoid a fire that could substantially reduce habitat of chipmunks over a mountain range.

The logistic model for predicting the non-gonoactive Aedes aegypti females.

PubMed

Reyes-Villanueva, Filiberto; Rodríguez-Pérez, Mario A

2004-01-01

To estimate, using logistic regression, the likelihood of occurrence of a non-gonoactive Aedes aegypti female, previously fed human blood, with relation to body size and collection method. This study was conducted in Monterrey, Mexico, between 1994 and 1996. Ten samplings of 60 mosquitoes of Ae. aegypti females were carried out in three dengue endemic areas: six of biting females, two of emerging mosquitoes, and two of indoor resting females. Gravid females, as well as those with blood in the gut were removed. Mosquitoes were taken to the laboratory and engorged on human blood. After 48 hours, ovaries were dissected to register whether they were gonoactive or non-gonoactive. Wing-length in mm was an indicator for body size. The logistic regression model was used to assess the likelihood of non-gonoactivity, as a binary variable, in relation to wing-length and collection method. Of the 600 females, 164 (27%) remained non-gonoactive, with a wing-length range of 1.9-3.2 mm, almost equal to that of all females (1.8-3.3 mm). The logistic regression model showed a significant likelihood of a female remaining non-gonoactive (Y=1). The collection method did not influence the binary response, but there was an inverse relationship between non-gonoactivity and wing-length. Dengue vector populations from Monterrey, Mexico display a wide-range body size. Logistic regression was a useful tool to estimate the likelihood for an engorged female to remain non-gonoactive. The necessity for a second blood meal is present in any female, but small mosquitoes are more likely to bite again within a 2-day interval, in order to attain egg maturation. The English version of this paper is available too at: http://www.insp.mx/salud/index.html.

Monitoring heavy metal Cr in soil based on hyperspectral data using regression analysis

NASA Astrophysics Data System (ADS)

Zhang, Ningyu; Xu, Fuyun; Zhuang, Shidong; He, Changwei

2016-10-01

Heavy metal pollution in soils is one of the most critical problems in the global ecology and environment safety nowadays. Hyperspectral remote sensing and its application is capable of high speed, low cost, less risk and less damage, and provides a good method for detecting heavy metals in soil. This paper proposed a new idea of applying regression analysis of stepwise multiple regression between the spectral data and monitoring the amount of heavy metal Cr by sample points in soil for environmental protection. In the measurement, a FieldSpec HandHeld spectroradiometer is used to collect reflectance spectra of sample points over the wavelength range of 325-1075 nm. Then the spectral data measured by the spectroradiometer is preprocessed to reduced the influence of the external factors, and the preprocessed methods include first-order differential equation, second-order differential equation and continuum removal method. The algorithms of stepwise multiple regression are established accordingly, and the accuracy of each equation is tested. The results showed that the accuracy of first-order differential equation works best, which makes it feasible to predict the content of heavy metal Cr by using stepwise multiple regression.

Stochastic dynamics and logistic population growth

NASA Astrophysics Data System (ADS)

Méndez, Vicenç; Assaf, Michael; Campos, Daniel; Horsthemke, Werner

2015-06-01

The Verhulst model is probably the best known macroscopic rate equation in population ecology. It depends on two parameters, the intrinsic growth rate and the carrying capacity. These parameters can be estimated for different populations and are related to the reproductive fitness and the competition for limited resources, respectively. We investigate analytically and numerically the simplest possible microscopic scenarios that give rise to the logistic equation in the deterministic mean-field limit. We provide a definition of the two parameters of the Verhulst equation in terms of microscopic parameters. In addition, we derive the conditions for extinction or persistence of the population by employing either the momentum-space spectral theory or the real-space Wentzel-Kramers-Brillouin approximation to determine the probability distribution function and the mean time to extinction of the population. Our analytical results agree well with numerical simulations.

The Application of the Cumulative Logistic Regression Model to Automated Essay Scoring

ERIC Educational Resources Information Center

Haberman, Shelby J.; Sinharay, Sandip

2010-01-01

Most automated essay scoring programs use a linear regression model to predict an essay score from several essay features. This article applied a cumulative logit model instead of the linear regression model to automated essay scoring. Comparison of the performances of the linear regression model and the cumulative logit model was performed on a…

Mean annual runoff and peak flow estimates based on channel geometry of streams in northeastern and western Montana

USGS Publications Warehouse

Parrett, Charles; Omang, R.J.; Hull, J.A.

1983-01-01

Equations for estimating mean annual runoff and peak discharge from measurements of channel geometry were developed for western and northeastern Montana. The study area was divided into two regions for the mean annual runoff analysis, and separate multiple-regression equations were developed for each region. The active-channel width was determined to be the most important independent variable in each region. The standard error of estimate for the estimating equation using active-channel width was 61 percent in the Northeast Region and 38 percent in the West region. The study area was divided into six regions for the peak discharge analysis, and multiple regression equations relating channel geometry and basin characteristics to peak discharges having recurrence intervals of 2, 5, 10, 25, 50 and 100 years were developed for each region. The standard errors of estimate for the regression equations using only channel width as an independent variable ranged from 35 to 105 percent. The standard errors improved in four regions as basin characteristics were added to the estimating equations. (USGS)

Estimation of premorbid general fluid intelligence using traditional Chinese reading performance in Taiwanese samples.

PubMed

Chen, Ying-Jen; Ho, Meng-Yang; Chen, Kwan-Ju; Hsu, Chia-Fen; Ryu, Shan-Jin

2009-08-01

The aims of the present study were to (i) investigate if traditional Chinese word reading ability can be used for estimating premorbid general intelligence; and (ii) to provide multiple regression equations for estimating premorbid performance on Raven's Standard Progressive Matrices (RSPM), using age, years of education and Chinese Graded Word Reading Test (CGWRT) scores as predictor variables. Four hundred and twenty-six healthy volunteers (201 male, 225 female), aged 16-93 years (mean +/- SD, 41.92 +/- 18.19 years) undertook the tests individually under supervised conditions. Seventy percent of subjects were randomly allocated to the derivation group (n = 296), and the rest to the validation group (n = 130). RSPM score was positively correlated with CGWRT score and years of education. RSPM and CGWRT scores and years of education were also inversely correlated with age, but the declining trend for RSPM performance against age was steeper than that for CGWRT performance. Separate multiple regression equations were derived for estimating RSPM scores using different combinations of age, years of education, and CGWRT score for both groups. The multiple regression coefficient of each equation ranged from 0.71 to 0.80 with the standard error of estimate between 7 and 8 RSPM points. When fitting the data of one group to the equations derived from its counterpart group, the cross-validation multiple regression coefficients ranged from 0.71 to 0.79. There were no significant differences in the 'predicted-obtained' RSPM discrepancies between any equations. The regression equations derived in the present study may provide a basis for estimating premorbid RSPM performance.

Estimating air drying times of lumber with multiple regression

Treesearch

William T. Simpson

2004-01-01

In this study, the applicability of a multiple regression equation for estimating air drying times of red oak, sugar maple, and ponderosa pine lumber was evaluated. The equation allows prediction of estimated air drying times from historic weather records of temperature and relative humidity at any desired location.

National scale biomass estimators for United States tree species

Treesearch

Jennifer C. Jenkins; David C. Chojnacky; Linda S. Heath; Richard A. Birdsey

2003-01-01

Estimates of national-scale forest carbon (C) stocks and fluxes are typically based on allometric regression equations developed using dimensional analysis techniques. However, the literature is inconsistent and incomplete with respect to large-scale forest C estimation. We compiled all available diameter-based allometric regression equations for estimating total...

Data-driven discovery of partial differential equations

PubMed Central

Rudy, Samuel H.; Brunton, Steven L.; Proctor, Joshua L.; Kutz, J. Nathan

2017-01-01

We propose a sparse regression method capable of discovering the governing partial differential equation(s) of a given system by time series measurements in the spatial domain. The regression framework relies on sparsity-promoting techniques to select the nonlinear and partial derivative terms of the governing equations that most accurately represent the data, bypassing a combinatorially large search through all possible candidate models. The method balances model complexity and regression accuracy by selecting a parsimonious model via Pareto analysis. Time series measurements can be made in an Eulerian framework, where the sensors are fixed spatially, or in a Lagrangian framework, where the sensors move with the dynamics. The method is computationally efficient, robust, and demonstrated to work on a variety of canonical problems spanning a number of scientific domains including Navier-Stokes, the quantum harmonic oscillator, and the diffusion equation. Moreover, the method is capable of disambiguating between potentially nonunique dynamical terms by using multiple time series taken with different initial data. Thus, for a traveling wave, the method can distinguish between a linear wave equation and the Korteweg–de Vries equation, for instance. The method provides a promising new technique for discovering governing equations and physical laws in parameterized spatiotemporal systems, where first-principles derivations are intractable. PMID:28508044

Biological Applications in the Mathematics Curriculum

ERIC Educational Resources Information Center

Marland, Eric; Palmer, Katrina M.; Salinas, Rene A.

2008-01-01

In this article we provide two detailed examples of how we incorporate biological examples into two mathematics courses: Linear Algebra and Ordinary Differential Equations. We use Leslie matrix models to demonstrate the biological properties of eigenvalues and eigenvectors. For Ordinary Differential Equations, we show how using a logistic growth…

Widen NomoGram for multinomial logistic regression: an application to staging liver fibrosis in chronic hepatitis C patients.

PubMed

Ardoino, Ilaria; Lanzoni, Monica; Marano, Giuseppe; Boracchi, Patrizia; Sagrini, Elisabetta; Gianstefani, Alice; Piscaglia, Fabio; Biganzoli, Elia M

2017-04-01

The interpretation of regression models results can often benefit from the generation of nomograms, 'user friendly' graphical devices especially useful for assisting the decision-making processes. However, in the case of multinomial regression models, whenever categorical responses with more than two classes are involved, nomograms cannot be drawn in the conventional way. Such a difficulty in managing and interpreting the outcome could often result in a limitation of the use of multinomial regression in decision-making support. In the present paper, we illustrate the derivation of a non-conventional nomogram for multinomial regression models, intended to overcome this issue. Although it may appear less straightforward at first sight, the proposed methodology allows an easy interpretation of the results of multinomial regression models and makes them more accessible for clinicians and general practitioners too. Development of prediction model based on multinomial logistic regression and of the pertinent graphical tool is illustrated by means of an example involving the prediction of the extent of liver fibrosis in hepatitis C patients by routinely available markers.

Comparison of methods for the prediction of human clearance from hepatocyte intrinsic clearance for a set of reference compounds and an external evaluation set.

PubMed

Yamagata, Tetsuo; Zanelli, Ugo; Gallemann, Dieter; Perrin, Dominique; Dolgos, Hugues; Petersson, Carl

2017-09-01

1. We compared direct scaling, regression model equation and the so-called "Poulin et al." methods to scale clearance (CL) from in vitro intrinsic clearance (CL int ) measured in human hepatocytes using two sets of compounds. One reference set comprised of 20 compounds with known elimination pathways and one external evaluation set based on 17 compounds development in Merck (MS). 2. A 90% prospective confidence interval was calculated using the reference set. This interval was found relevant for the regression equation method. The three outliers identified were justified on the basis of their elimination mechanism. 3. The direct scaling method showed a systematic underestimation of clearance in both the reference and evaluation sets. The "Poulin et al." and the regression equation methods showed no obvious bias in either the reference or evaluation sets. 4. The regression model equation was slightly superior to the "Poulin et al." method in the reference set and showed a better absolute average fold error (AAFE) of value 1.3 compared to 1.6. A larger difference was observed in the evaluation set were the regression method and "Poulin et al." resulted in an AAFE of 1.7 and 2.6, respectively (removing the three compounds with known issues mentioned above). A similar pattern was observed for the correlation coefficient. Based on these data we suggest the regression equation method combined with a prospective confidence interval as the first choice for the extrapolation of human in vivo hepatic metabolic clearance from in vitro systems.

Predicting hepatic steatosis and liver fat content in obese children based on biochemical parameters and anthropometry.

PubMed

Zhang, H-X; Xu, X-Q; Fu, J-F; Lai, C; Chen, X-F

2015-04-01

Predictors of quantitative evaluation of hepatic steatosis and liver fat content (LFC) using clinical and laboratory variables available in the general practice in the obese children are poorly identified. To build predictive models of hepatic steatosis and LFC in obese children based on biochemical parameters and anthropometry. Hepatic steatosis and LFC were determined using proton magnetic resonance spectroscopy in 171 obese children aged 5.5-18.0 years. Routine clinical and laboratory parameters were also measured in all subjects. Group analysis, univariable correlation analysis, and multivariate logistic and linear regression analysis were used to develop a liver fat score to identify hepatic steatosis and a liver fat equation to predict LFC in each subject. The predictive model of hepatic steatosis in our participants based on waist circumference and alanine aminotransferase had an area under the receiver operating characteristic curve of 0.959 (95% confidence interval: 0.927-0.990). The optimal cut-off value of 0.525 for determining hepatic steatosis had sensitivity of 93% and specificity of 90%. A liver fat equation was also developed based on the same parameters of hepatic steatosis liver fat score, which would be used to calculate the LFC in each individual. The liver fat score and liver fat equation, consisting of routinely available variables, may help paediatricians to accurately determine hepatic steatosis and LFC in clinical practice, but external validation is needed before it can be employed for this purpose. © 2014 The Authors. Pediatric Obesity © 2014 World Obesity.

Regularization Paths for Conditional Logistic Regression: The clogitL1 Package.

PubMed

Reid, Stephen; Tibshirani, Rob

2014-07-01

We apply the cyclic coordinate descent algorithm of Friedman, Hastie, and Tibshirani (2010) to the fitting of a conditional logistic regression model with lasso [Formula: see text] and elastic net penalties. The sequential strong rules of Tibshirani, Bien, Hastie, Friedman, Taylor, Simon, and Tibshirani (2012) are also used in the algorithm and it is shown that these offer a considerable speed up over the standard coordinate descent algorithm with warm starts. Once implemented, the algorithm is used in simulation studies to compare the variable selection and prediction performance of the conditional logistic regression model against that of its unconditional (standard) counterpart. We find that the conditional model performs admirably on datasets drawn from a suitable conditional distribution, outperforming its unconditional counterpart at variable selection. The conditional model is also fit to a small real world dataset, demonstrating how we obtain regularization paths for the parameters of the model and how we apply cross validation for this method where natural unconditional prediction rules are hard to come by.

Computational tools for exact conditional logistic regression.

PubMed

Corcoran, C; Mehta, C; Patel, N; Senchaudhuri, P

Logistic regression analyses are often challenged by the inability of unconditional likelihood-based approximations to yield consistent, valid estimates and p-values for model parameters. This can be due to sparseness or separability in the data. Conditional logistic regression, though useful in such situations, can also be computationally unfeasible when the sample size or number of explanatory covariates is large. We review recent developments that allow efficient approximate conditional inference, including Monte Carlo sampling and saddlepoint approximations. We demonstrate through real examples that these methods enable the analysis of significantly larger and more complex data sets. We find in this investigation that for these moderately large data sets Monte Carlo seems a better alternative, as it provides unbiased estimates of the exact results and can be executed in less CPU time than can the single saddlepoint approximation. Moreover, the double saddlepoint approximation, while computationally the easiest to obtain, offers little practical advantage. It produces unreliable results and cannot be computed when a maximum likelihood solution does not exist. Copyright 2001 John Wiley & Sons, Ltd.

Regularization Paths for Conditional Logistic Regression: The clogitL1 Package

PubMed Central

Reid, Stephen; Tibshirani, Rob

2014-01-01

We apply the cyclic coordinate descent algorithm of Friedman, Hastie, and Tibshirani (2010) to the fitting of a conditional logistic regression model with lasso (ℓ1) and elastic net penalties. The sequential strong rules of Tibshirani, Bien, Hastie, Friedman, Taylor, Simon, and Tibshirani (2012) are also used in the algorithm and it is shown that these offer a considerable speed up over the standard coordinate descent algorithm with warm starts. Once implemented, the algorithm is used in simulation studies to compare the variable selection and prediction performance of the conditional logistic regression model against that of its unconditional (standard) counterpart. We find that the conditional model performs admirably on datasets drawn from a suitable conditional distribution, outperforming its unconditional counterpart at variable selection. The conditional model is also fit to a small real world dataset, demonstrating how we obtain regularization paths for the parameters of the model and how we apply cross validation for this method where natural unconditional prediction rules are hard to come by. PMID:26257587

Ordinal logistic regression analysis on the nutritional status of children in KarangKitri village

NASA Astrophysics Data System (ADS)

Ohyver, Margaretha; Yongharto, Kimmy Octavian

2015-09-01

Ordinal logistic regression is a statistical technique that can be used to describe the relationship between ordinal response variable with one or more independent variables. This method has been used in various fields including in the health field. In this research, ordinal logistic regression is used to describe the relationship between nutritional status of children with age, gender, height, and family status. Nutritional status of children in this research is divided into over nutrition, well nutrition, less nutrition, and malnutrition. The purpose for this research is to describe the characteristics of children in the KarangKitri Village and to determine the factors that influence the nutritional status of children in the KarangKitri village. There are three things that obtained from this research. First, there are still children who are not categorized as well nutritional status. Second, there are children who come from sufficient economic level which include in not normal status. Third, the factors that affect the nutritional level of children are age, family status, and height.

Analysis of an Environmental Exposure Health Questionnaire in a Metropolitan Minority Population Utilizing Logistic Regression and Support Vector Machines

PubMed Central

Chen, Chau-Kuang; Bruce, Michelle; Tyler, Lauren; Brown, Claudine; Garrett, Angelica; Goggins, Susan; Lewis-Polite, Brandy; Weriwoh, Mirabel L; Juarez, Paul D.; Hood, Darryl B.; Skelton, Tyler

2014-01-01

The goal of this study was to analyze a 54-item instrument for assessment of perception of exposure to environmental contaminants within the context of the built environment, or exposome. This exposome was defined in five domains to include 1) home and hobby, 2) school, 3) community, 4) occupation, and 5) exposure history. Interviews were conducted with child-bearing-age minority women at Metro Nashville General Hospital at Meharry Medical College. Data were analyzed utilizing DTReg software for Support Vector Machine (SVM) modeling followed by an SPSS package for a logistic regression model. The target (outcome) variable of interest was respondent's residence by ZIP code. The results demonstrate that the rank order of important variables with respect to SVM modeling versus traditional logistic regression models is almost identical. This is the first study documenting that SVM analysis has discriminate power for determination of higher-ordered spatial relationships on an environmental exposure history questionnaire. PMID:23395953

An ultra low power feature extraction and classification system for wearable seizure detection.

PubMed

Page, Adam; Pramod Tim Oates, Siddharth; Mohsenin, Tinoosh

2015-01-01

In this paper we explore the use of a variety of machine learning algorithms for designing a reliable and low-power, multi-channel EEG feature extractor and classifier for predicting seizures from electroencephalographic data (scalp EEG). Different machine learning classifiers including k-nearest neighbor, support vector machines, naïve Bayes, logistic regression, and neural networks are explored with the goal of maximizing detection accuracy while minimizing power, area, and latency. The input to each machine learning classifier is a 198 feature vector containing 9 features for each of the 22 EEG channels obtained over 1-second windows. All classifiers were able to obtain F1 scores over 80% and onset sensitivity of 100% when tested on 10 patients. Among five different classifiers that were explored, logistic regression (LR) proved to have minimum hardware complexity while providing average F-1 score of 91%. Both ASIC and FPGA implementations of logistic regression are presented and show the smallest area, power consumption, and the lowest latency when compared to the previous work.

The arcsine is asinine: the analysis of proportions in ecology.

PubMed

Warton, David I; Hui, Francis K C

2011-01-01

The arcsine square root transformation has long been standard procedure when analyzing proportional data in ecology, with applications in data sets containing binomial and non-binomial response variables. Here, we argue that the arcsine transform should not be used in either circumstance. For binomial data, logistic regression has greater interpretability and higher power than analyses of transformed data. However, it is important to check the data for additional unexplained variation, i.e., overdispersion, and to account for it via the inclusion of random effects in the model if found. For non-binomial data, the arcsine transform is undesirable on the grounds of interpretability, and because it can produce nonsensical predictions. The logit transformation is proposed as an alternative approach to address these issues. Examples are presented in both cases to illustrate these advantages, comparing various methods of analyzing proportions including untransformed, arcsine- and logit-transformed linear models and logistic regression (with or without random effects). Simulations demonstrate that logistic regression usually provides a gain in power over other methods.

Analysis of an environmental exposure health questionnaire in a metropolitan minority population utilizing logistic regression and Support Vector Machines.

PubMed

Chen, Chau-Kuang; Bruce, Michelle; Tyler, Lauren; Brown, Claudine; Garrett, Angelica; Goggins, Susan; Lewis-Polite, Brandy; Weriwoh, Mirabel L; Juarez, Paul D; Hood, Darryl B; Skelton, Tyler

2013-02-01

The goal of this study was to analyze a 54-item instrument for assessment of perception of exposure to environmental contaminants within the context of the built environment, or exposome. This exposome was defined in five domains to include 1) home and hobby, 2) school, 3) community, 4) occupation, and 5) exposure history. Interviews were conducted with child-bearing-age minority women at Metro Nashville General Hospital at Meharry Medical College. Data were analyzed utilizing DTReg software for Support Vector Machine (SVM) modeling followed by an SPSS package for a logistic regression model. The target (outcome) variable of interest was respondent's residence by ZIP code. The results demonstrate that the rank order of important variables with respect to SVM modeling versus traditional logistic regression models is almost identical. This is the first study documenting that SVM analysis has discriminate power for determination of higher-ordered spatial relationships on an environmental exposure history questionnaire.

Paleoflood investigations to improve peak-streamflow regional-regression equations for natural streamflow in eastern Colorado, 2015

USGS Publications Warehouse

Kohn, Michael S.; Stevens, Michael R.; Harden, Tessa M.; Godaire, Jeanne E.; Klinger, Ralph E.; Mommandi, Amanullah

2016-09-09

The U.S. Geological Survey (USGS), in cooperation with the Colorado Department of Transportation, developed regional-regression equations for estimating the 50-, 20-, 10-, 4-, 2-, 1-, 0.5-, 0.2-percent annual exceedance-probability discharge (AEPD) for natural streamflow in eastern Colorado. A total of 188 streamgages, consisting of 6,536 years of record and a mean of approximately 35 years of record per streamgage, were used to develop the peak-streamflow regional-regression equations. The estimated AEPDs for each streamgage were computed using the USGS software program PeakFQ. The AEPDs were determined using systematic data through water year 2013. Based on previous studies conducted in Colorado and neighboring States and on the availability of data, 72 characteristics (57 basin and 15 climatic characteristics) were evaluated as candidate explanatory variables in the regression analysis. Paleoflood and non-exceedance bound ages were established based on reconnaissance-level methods. Multiple lines of evidence were used at each streamgage to arrive at a conclusion (age estimate) to add a higher degree of certainty to reconnaissance-level estimates. Paleoflood or nonexceedance bound evidence was documented at 41 streamgages, and 3 streamgages had previously collected paleoflood data.To determine the peak discharge of a paleoflood or non-exceedanc bound, two different hydraulic models were used.The mean standard error of prediction (SEP) for all 8 AEPDs was reduced approximately 25 percent compared to the previous flood-frequency study. For paleoflood data to be effective in reducing the SEP in eastern Colorado, a larger ratio than 44 of 188 (23 percent) streamgages would need paleoflood data and that paleoflood data would need to increase the record length by more than 25 years for the 1-percent AEPD. The greatest reduction in SEP for the peak-streamflow regional-regression equations was observed when additional new basin characteristics were included in the peak-streamflow regional-regression equations and when eastern Colorado was divided into two separate hydrologic regions. To make further reductions in the uncertainties of the peak-streamflow regional-regression equations in the Foothills and Plains hydrologic regions, additional streamgages or crest-stage gages are needed to collect peak-streamflow data on natural streams in eastern Colorado.Generalized-Least Squares regression was used to compute the final peak-streamflow regional-regression equations for peak-streamflow. Dividing eastern Colorado into two new individual regions at –104° longitude resulted in peak-streamflow regional-regression equations with the smallest SEP. The new hydrologic region located between –104° longitude and the Kansas-Nebraska State line will be designated the Plains hydrologic region and the hydrologic region comprising the rest of eastern Colorado located west of the –104° longitude and east of the Rocky Mountains and below 7,500 feet in the South Platte River Basin and below 9,000 feet in the Arkansas River Basin will be designated the Foothills hydrologic region.

A Modified Double Multiple Nonlinear Regression Constitutive Equation for Modeling and Prediction of High Temperature Flow Behavior of BFe10-1-2 Alloy

NASA Astrophysics Data System (ADS)

Cai, Jun; Wang, Kuaishe; Shi, Jiamin; Wang, Wen; Liu, Yingying

2018-01-01

Constitutive analysis for hot working of BFe10-1-2 alloy was carried out by using experimental stress-strain data from isothermal hot compression tests, in a wide range of temperature of 1,023 1,273 K, and strain rate range of 0.001 10 s-1. A constitutive equation based on modified double multiple nonlinear regression was proposed considering the independent effects of strain, strain rate, temperature and their interrelation. The predicted flow stress data calculated from the developed equation was compared with the experimental data. Correlation coefficient (R), average absolute relative error (AARE) and relative errors were introduced to verify the validity of the developed constitutive equation. Subsequently, a comparative study was made on the capability of strain-compensated Arrhenius-type constitutive model. The results showed that the developed constitutive equation based on modified double multiple nonlinear regression could predict flow stress of BFe10-1-2 alloy with good correlation and generalization.

Prescription-drug-related risk in driving: comparing conventional and lasso shrinkage logistic regressions.

PubMed

Avalos, Marta; Adroher, Nuria Duran; Lagarde, Emmanuel; Thiessard, Frantz; Grandvalet, Yves; Contrand, Benjamin; Orriols, Ludivine

2012-09-01

Large data sets with many variables provide particular challenges when constructing analytic models. Lasso-related methods provide a useful tool, although one that remains unfamiliar to most epidemiologists. We illustrate the application of lasso methods in an analysis of the impact of prescribed drugs on the risk of a road traffic crash, using a large French nationwide database (PLoS Med 2010;7:e1000366). In the original case-control study, the authors analyzed each exposure separately. We use the lasso method, which can simultaneously perform estimation and variable selection in a single model. We compare point estimates and confidence intervals using (1) a separate logistic regression model for each drug with a Bonferroni correction and (2) lasso shrinkage logistic regression analysis. Shrinkage regression had little effect on (bias corrected) point estimates, but led to less conservative results, noticeably for drugs with moderate levels of exposure. Carbamates, carboxamide derivative and fatty acid derivative antiepileptics, drugs used in opioid dependence, and mineral supplements of potassium showed stronger associations. Lasso is a relevant method in the analysis of databases with large number of exposures and can be recommended as an alternative to conventional strategies.

Spatiotemporal variability of urban growth factors: A global and local perspective on the megacity of Mumbai

NASA Astrophysics Data System (ADS)

Shafizadeh-Moghadam, Hossein; Helbich, Marco

2015-03-01

The rapid growth of megacities requires special attention among urban planners worldwide, and particularly in Mumbai, India, where growth is very pronounced. To cope with the planning challenges this will bring, developing a retrospective understanding of urban land-use dynamics and the underlying driving-forces behind urban growth is a key prerequisite. This research uses regression-based land-use change models - and in particular non-spatial logistic regression models (LR) and auto-logistic regression models (ALR) - for the Mumbai region over the period 1973-2010, in order to determine the drivers behind spatiotemporal urban expansion. Both global models are complemented by a local, spatial model, the so-called geographically weighted logistic regression (GWLR) model, one that explicitly permits variations in driving-forces across space. The study comes to two main conclusions. First, both global models suggest similar driving-forces behind urban growth over time, revealing that LRs and ALRs result in estimated coefficients with comparable magnitudes. Second, all the local coefficients show distinctive temporal and spatial variations. It is therefore concluded that GWLR aids our understanding of urban growth processes, and so can assist context-related planning and policymaking activities when seeking to secure a sustainable urban future.

Methods for estimating peak-flow frequencies at ungaged sites in Montana based on data through water year 2011: Chapter F in Montana StreamStats

USGS Publications Warehouse

Sando, Roy; Sando, Steven K.; McCarthy, Peter M.; Dutton, DeAnn M.

2016-04-05

The U.S. Geological Survey (USGS), in cooperation with the Montana Department of Natural Resources and Conservation, completed a study to update methods for estimating peak-flow frequencies at ungaged sites in Montana based on peak-flow data at streamflow-gaging stations through water year 2011. The methods allow estimation of peak-flow frequencies (that is, peak-flow magnitudes, in cubic feet per second, associated with annual exceedance probabilities of 66.7, 50, 42.9, 20, 10, 4, 2, 1, 0.5, and 0.2 percent) at ungaged sites. The annual exceedance probabilities correspond to 1.5-, 2-, 2.33-, 5-, 10-, 25-, 50-, 100-, 200-, and 500-year recurrence intervals, respectively.Regional regression analysis is a primary focus of Chapter F of this Scientific Investigations Report, and regression equations for estimating peak-flow frequencies at ungaged sites in eight hydrologic regions in Montana are presented. The regression equations are based on analysis of peak-flow frequencies and basin characteristics at 537 streamflow-gaging stations in or near Montana and were developed using generalized least squares regression or weighted least squares regression.All of the data used in calculating basin characteristics that were included as explanatory variables in the regression equations were developed for and are available through the USGS StreamStats application (http://water.usgs.gov/osw/streamstats/) for Montana. StreamStats is a Web-based geographic information system application that was created by the USGS to provide users with access to an assortment of analytical tools that are useful for water-resource planning and management. The primary purpose of the Montana StreamStats application is to provide estimates of basin characteristics and streamflow characteristics for user-selected ungaged sites on Montana streams. The regional regression equations presented in this report chapter can be conveniently solved using the Montana StreamStats application.Selected results from this study were compared with results of previous studies. For most hydrologic regions, the regression equations reported for this study had lower mean standard errors of prediction (in percent) than the previously reported regression equations for Montana. The equations presented for this study are considered to be an improvement on the previously reported equations primarily because this study (1) included 13 more years of peak-flow data; (2) included 35 more streamflow-gaging stations than previous studies; (3) used a detailed geographic information system (GIS)-based definition of the regulation status of streamflow-gaging stations, which allowed better determination of the unregulated peak-flow records that are appropriate for use in the regional regression analysis; (4) included advancements in GIS and remote-sensing technologies, which allowed more convenient calculation of basin characteristics and investigation of many more candidate basin characteristics; and (5) included advancements in computational and analytical methods, which allowed more thorough and consistent data analysis.This report chapter also presents other methods for estimating peak-flow frequencies at ungaged sites. Two methods for estimating peak-flow frequencies at ungaged sites located on the same streams as streamflow-gaging stations are described. Additionally, envelope curves relating maximum recorded annual peak flows to contributing drainage area for each of the eight hydrologic regions in Montana are presented and compared to a national envelope curve. In addition to providing general information on characteristics of large peak flows, the regional envelope curves can be used to assess the reasonableness of peak-flow frequency estimates determined using the regression equations.

Advanced Targeting Cost Function Design for Evolutionary Optimization of Control of Logistic Equation

NASA Astrophysics Data System (ADS)

Senkerik, Roman; Zelinka, Ivan; Davendra, Donald; Oplatkova, Zuzana

2010-06-01

This research deals with the optimization of the control of chaos by means of evolutionary algorithms. This work is aimed on an explanation of how to use evolutionary algorithms (EAs) and how to properly define the advanced targeting cost function (CF) securing very fast and precise stabilization of desired state for any initial conditions. As a model of deterministic chaotic system, the one dimensional Logistic equation was used. The evolutionary algorithm Self-Organizing Migrating Algorithm (SOMA) was used in four versions. For each version, repeated simulations were conducted to outline the effectiveness and robustness of used method and targeting CF.

eHealth Literacy: Predictors in a Population With Moderate-to-High Cardiovascular Risk

PubMed Central

Richtering, Sarah S; Hyun, Karice; Neubeck, Lis; Coorey, Genevieve; Chalmers, John; Usherwood, Tim; Peiris, David; Chow, Clara K

2017-01-01

Background Electronic health (eHealth) literacy is a growing area of research parallel to the ongoing development of eHealth interventions. There is, however, little and conflicting information regarding the factors that influence eHealth literacy, notably in chronic disease. We are similarly ill-informed about the relationship between eHealth and health literacy, 2 related yet distinct health-related literacies. Objective The aim of our study was to investigate the demographic, socioeconomic, technology use, and health literacy predictors of eHealth literacy in a population with moderate-to-high cardiovascular risk. Methods Demographic and socioeconomic data were collected from 453 participants of the CONNECT (Consumer Navigation of Electronic Cardiovascular Tools) study, which included age, gender, education, income, cardiovascular-related polypharmacy, private health care, main electronic device use, and time spent on the Internet. Participants also completed an eHealth Literacy Scale (eHEALS) and a Health Literacy Questionnaire (HLQ). Univariate analyses were performed to compare patient demographic and socioeconomic characteristics between the low (eHEALS<26) and high (eHEALS≥26) eHealth literacy groups. To then determine the predictors of low eHealth literacy, multiple-adjusted generalized estimating equation logistic regression model was used. This technique was also used to examine the correlation between eHealth literacy and health literacy for 4 predefined literacy themes: navigating resources, skills to use resources, usefulness for oneself, and critical evaluation. Results The univariate analysis showed that patients with lower eHealth literacy were older (68 years vs 66 years, P=.01), had lower level of education (P=.007), and spent less time on the Internet (P<.001). However, multiple-adjusted generalized estimating equation logistic regression model demonstrated that only the time spent on the Internet (P=.01) was associated with the level of eHealth literacy. Regarding the comparison between the eHEALS items and HLQ scales, a positive linear relationship was found for the themes “usefulness for oneself” (P=.049) and “critical evaluation” (P=.01). Conclusions This study shows the importance of evaluating patients’ familiarity with the Internet as reflected, in part, by the time spent on the Internet. It also shows the importance of specifically assessing eHealth literacy in conjunction with a health literacy assessment in order to assess patients’ navigational knowledge and skills using the Internet, specific to the use of eHealth applications. PMID:28130203

Hospital-acquired pneumonia is an independent predictor of poor global outcome in severe traumatic brain injury up to 5 years after discharge.

PubMed

Kesinger, Matthew Ryan; Kumar, Raj G; Wagner, Amy K; Puyana, Juan Carlos; Peitzman, Andrew P; Billiar, Timothy R; Sperry, Jason L

2015-02-01

Long-term outcomes following traumatic brain injury (TBI) correlate with initial head injury severity and other acute factors. Hospital-acquired pneumonia (HAP) is a common complication in TBI. Limited information exists regarding the significance of infectious complications on long-term outcomes after TBI. We sought to characterize risks associated with HAP on outcomes 5 years after TBI. This study involved data from the merger of an institutional trauma registry and the Traumatic Brain Injury Model Systems outcome data. Individuals with severe head injuries (Abbreviated Injury Scale [AIS] score ≥ 4) who survived to rehabilitation were analyzed. Primary outcome was Glasgow Outcome Scale-Extended (GOSE) at 1, 2, and 5 years. GOSE was dichotomized into low (GOSE score < 6) and high (GOSE score ≥ 6). Logistic regression was used to determine adjusted odds of low GOSE score associated with HAP after controlling for age, sex, head and overall injury severity, cranial surgery, Glasgow Coma Scale (GCS) score, ventilation days, and other important confounders. A general estimating equation model was used to analyze all outcome observations simultaneously while controlling for within-patient correlation. A total of 141 individuals met inclusion criteria, with a 30% incidence of HAP. Individuals with and without HAP had similar demographic profiles, presenting vitals, head injury severity, and prevalence of cranial surgery. Individuals with HAP had lower presenting GCS score. Logistic regression demonstrated that HAP was independently associated with low GOSE scores at follow-up (1 year: odds ratio [OR], 6.39; 95% confidence interval [CI], 1.76-23.14; p = 0.005) (2 years: OR, 7.30; 95% CI, 1.87-27.89; p = 0.004) (5-years: OR, 6.89; 95% CI, 1.42-33.39; p = 0.017). Stratifying by GCS score of 8 or lower and early intubation, HAP remained a significant independent predictor of low GOSE score in all strata. In the general estimating equation model, HAP continued to be an independent predictor of low GOSE score (OR, 4.59; 95% CI, 1.82-11.60; p = 0.001). HAP is independently associated with poor outcomes in severe TBI extending 5 years after injury. This suggests that precautions should be taken to reduce the risk of HAP in individuals with severe TBI. Prognostic study, level III.

Can Predictive Modeling Identify Head and Neck Oncology Patients at Risk for Readmission?

PubMed

Manning, Amy M; Casper, Keith A; Peter, Kay St; Wilson, Keith M; Mark, Jonathan R; Collar, Ryan M

2018-05-01

Objective Unplanned readmission within 30 days is a contributor to health care costs in the United States. The use of predictive modeling during hospitalization to identify patients at risk for readmission offers a novel approach to quality improvement and cost reduction. Study Design Two-phase study including retrospective analysis of prospectively collected data followed by prospective longitudinal study. Setting Tertiary academic medical center. Subjects and Methods Prospectively collected data for patients undergoing surgical treatment for head and neck cancer from January 2013 to January 2015 were used to build predictive models for readmission within 30 days of discharge using logistic regression, classification and regression tree (CART) analysis, and random forests. One model (logistic regression) was then placed prospectively into the discharge workflow from March 2016 to May 2016 to determine the model's ability to predict which patients would be readmitted within 30 days. Results In total, 174 admissions had descriptive data. Thirty-two were excluded due to incomplete data. Logistic regression, CART, and random forest predictive models were constructed using the remaining 142 admissions. When applied to 106 consecutive prospective head and neck oncology patients at the time of discharge, the logistic regression model predicted readmissions with a specificity of 94%, a sensitivity of 47%, a negative predictive value of 90%, and a positive predictive value of 62% (odds ratio, 14.9; 95% confidence interval, 4.02-55.45). Conclusion Prospectively collected head and neck cancer databases can be used to develop predictive models that can accurately predict which patients will be readmitted. This offers valuable support for quality improvement initiatives and readmission-related cost reduction in head and neck cancer care.

Utility of an Abbreviated Dizziness Questionnaire to Differentiate between Causes of Vertigo and Guide Appropriate Referral: A Multicenter Prospective Blinded Study

PubMed Central

Roland, Lauren T.; Kallogjeri, Dorina; Sinks, Belinda C.; Rauch, Steven D.; Shepard, Neil T.; White, Judith A.; Goebel, Joel A.

2015-01-01

Objective Test performance of a focused dizziness questionnaire’s ability to discriminate between peripheral and non-peripheral causes of vertigo. Study Design Prospective multi-center Setting Four academic centers with experienced balance specialists Patients New dizzy patients Interventions A 32-question survey was given to participants. Balance specialists were blinded and a diagnosis was established for all participating patients within 6 months. Main outcomes Multinomial logistic regression was used to evaluate questionnaire performance in predicting final diagnosis and differentiating between peripheral and non-peripheral vertigo. Univariate and multivariable stepwise logistic regression were used to identify questions as significant predictors of the ultimate diagnosis. C-index was used to evaluate performance and discriminative power of the multivariable models. Results 437 patients participated in the study. Eight participants without confirmed diagnoses were excluded and 429 were included in the analysis. Multinomial regression revealed that the model had good overall predictive accuracy of 78.5% for the final diagnosis and 75.5% for differentiating between peripheral and non-peripheral vertigo. Univariate logistic regression identified significant predictors of three main categories of vertigo: peripheral, central and other. Predictors were entered into forward stepwise multivariable logistic regression. The discriminative power of the final models for peripheral, central and other causes were considered good as measured by c-indices of 0.75, 0.7 and 0.78, respectively. Conclusions This multicenter study demonstrates a focused dizziness questionnaire can accurately predict diagnosis for patients with chronic/relapsing dizziness referred to outpatient clinics. Additionally, this survey has significant capability to differentiate peripheral from non-peripheral causes of vertigo and may, in the future, serve as a screening tool for specialty referral. Clinical utility of this questionnaire to guide specialty referral is discussed. PMID:26485598

Utility of an Abbreviated Dizziness Questionnaire to Differentiate Between Causes of Vertigo and Guide Appropriate Referral: A Multicenter Prospective Blinded Study.

PubMed

Roland, Lauren T; Kallogjeri, Dorina; Sinks, Belinda C; Rauch, Steven D; Shepard, Neil T; White, Judith A; Goebel, Joel A

2015-12-01

Test performance of a focused dizziness questionnaire's ability to discriminate between peripheral and nonperipheral causes of vertigo. Prospective multicenter. Four academic centers with experienced balance specialists. New dizzy patients. A 32-question survey was given to participants. Balance specialists were blinded and a diagnosis was established for all participating patients within 6 months. Multinomial logistic regression was used to evaluate questionnaire performance in predicting final diagnosis and differentiating between peripheral and nonperipheral vertigo. Univariate and multivariable stepwise logistic regression were used to identify questions as significant predictors of the ultimate diagnosis. C-index was used to evaluate performance and discriminative power of the multivariable models. In total, 437 patients participated in the study. Eight participants without confirmed diagnoses were excluded and 429 were included in the analysis. Multinomial regression revealed that the model had good overall predictive accuracy of 78.5% for the final diagnosis and 75.5% for differentiating between peripheral and nonperipheral vertigo. Univariate logistic regression identified significant predictors of three main categories of vertigo: peripheral, central, and other. Predictors were entered into forward stepwise multivariable logistic regression. The discriminative power of the final models for peripheral, central, and other causes was considered good as measured by c-indices of 0.75, 0.7, and 0.78, respectively. This multicenter study demonstrates a focused dizziness questionnaire can accurately predict diagnosis for patients with chronic/relapsing dizziness referred to outpatient clinics. Additionally, this survey has significant capability to differentiate peripheral from nonperipheral causes of vertigo and may, in the future, serve as a screening tool for specialty referral. Clinical utility of this questionnaire to guide specialty referral is discussed.

Methods for estimating flow-duration and annual mean-flow statistics for ungaged streams in Oklahoma

USGS Publications Warehouse

Esralew, Rachel A.; Smith, S. Jerrod

2010-01-01

Flow statistics can be used to provide decision makers with surface-water information needed for activities such as water-supply permitting, flow regulation, and other water rights issues. Flow statistics could be needed at any location along a stream. Most often, streamflow statistics are needed at ungaged sites, where no flow data are available to compute the statistics. Methods are presented in this report for estimating flow-duration and annual mean-flow statistics for ungaged streams in Oklahoma. Flow statistics included the (1) annual (period of record), (2) seasonal (summer-autumn and winter-spring), and (3) 12 monthly duration statistics, including the 20th, 50th, 80th, 90th, and 95th percentile flow exceedances, and the annual mean-flow (mean of daily flows for the period of record). Flow statistics were calculated from daily streamflow information collected from 235 streamflow-gaging stations throughout Oklahoma and areas in adjacent states. A drainage-area ratio method is the preferred method for estimating flow statistics at an ungaged location that is on a stream near a gage. The method generally is reliable only if the drainage-area ratio of the two sites is between 0.5 and 1.5. Regression equations that relate flow statistics to drainage-basin characteristics were developed for the purpose of estimating selected flow-duration and annual mean-flow statistics for ungaged streams that are not near gaging stations on the same stream. Regression equations were developed from flow statistics and drainage-basin characteristics for 113 unregulated gaging stations. Separate regression equations were developed by using U.S. Geological Survey streamflow-gaging stations in regions with similar drainage-basin characteristics. These equations can increase the accuracy of regression equations used for estimating flow-duration and annual mean-flow statistics at ungaged stream locations in Oklahoma. Streamflow-gaging stations were grouped by selected drainage-basin characteristics by using a k-means cluster analysis. Three regions were identified for Oklahoma on the basis of the clustering of gaging stations and a manual delineation of distinguishable hydrologic and geologic boundaries: Region 1 (western Oklahoma excluding the Oklahoma and Texas Panhandles), Region 2 (north- and south-central Oklahoma), and Region 3 (eastern and central Oklahoma). A total of 228 regression equations (225 flow-duration regressions and three annual mean-flow regressions) were developed using ordinary least-squares and left-censored (Tobit) multiple-regression techniques. These equations can be used to estimate 75 flow-duration statistics and annual mean-flow for ungaged streams in the three regions. Drainage-basin characteristics that were statistically significant independent variables in the regression analyses were (1) contributing drainage area; (2) station elevation; (3) mean drainage-basin elevation; (4) channel slope; (5) percentage of forested canopy; (6) mean drainage-basin hillslope; (7) soil permeability; and (8) mean annual, seasonal, and monthly precipitation. The accuracy of flow-duration regression equations generally decreased from high-flow exceedance (low-exceedance probability) to low-flow exceedance (high-exceedance probability) . This decrease may have happened because a greater uncertainty exists for low-flow estimates and low-flow is largely affected by localized geology that was not quantified by the drainage-basin characteristics selected. The standard errors of estimate of regression equations for Region 1 (western Oklahoma) were substantially larger than those standard errors for other regions, especially for low-flow exceedances. These errors may be a result of greater variability in low flow because of increased irrigation activities in this region. Regression equations may not be reliable for sites where the drainage-basin characteristics are outside the range of values of independent vari

Prediction of cold and heat patterns using anthropometric measures based on machine learning.

PubMed

Lee, Bum Ju; Lee, Jae Chul; Nam, Jiho; Kim, Jong Yeol

2018-01-01

To examine the association of body shape with cold and heat patterns, to determine which anthropometric measure is the best indicator for discriminating between the two patterns, and to investigate whether using a combination of measures can improve the predictive power to diagnose these patterns. Based on a total of 4,859 subjects (3,000 women and 1,859 men), statistical analyses using binary logistic regression were performed to assess the significance of the difference and the predictive power of each anthropometric measure, and binary logistic regression and Naive Bayes with the variable selection technique were used to assess the improvement in the predictive power of the patterns using the combined measures. In women, the strongest indicators for determining the cold and heat patterns among anthropometric measures were body mass index (BMI) and rib circumference; in men, the best indicator was BMI. In experiments using a combination of measures, the values of the area under the receiver operating characteristic curve in women were 0.776 by Naive Bayes and 0.772 by logistic regression, and the values in men were 0.788 by Naive Bayes and 0.779 by logistic regression. Individuals with a higher BMI have a tendency toward a heat pattern in both women and men. The use of a combination of anthropometric measures can slightly improve the diagnostic accuracy. Our findings can provide fundamental information for the diagnosis of cold and heat patterns based on body shape for personalized medicine.