On Graphically Checking Goodness-of-fit of Binary Logistic Regression Models

2009 ◽  
Vol 48 (03) ◽  
pp. 306-310 ◽  
Author(s):  
C. E. Minder ◽  
G. Gillmann

Summary Objectives: This paper is concerned with checking goodness-of-fit of binary logistic regression models. For the practitioners of data analysis, the broad classes of procedures for checking goodness-of-fit available in the literature are described. The challenges of model checking in the context of binary logistic regression are reviewed. As a viable solution, a simple graphical procedure for checking goodness-of-fit is proposed. Methods: The graphical procedure proposed relies on pieces of information available from any logistic analysis; the focus is on combining and presenting these in an informative way. Results: The information gained using this approach is presented with three examples. In the discussion, the proposed method is put into context and compared with other graphical procedures for checking goodness-of-fit of binary logistic models available in the literature. Conclusion: A simple graphical method can significantly improve the understanding of any logistic regression analysis and help to prevent faulty conclusions.

Agronomy ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. 17 ◽  
Author(s):  
Manuel Díaz-Pérez ◽  
Ángel Carreño-Ortega ◽  
José-Antonio Salinas-Andújar ◽  
Ángel-Jesús Callejón-Ferre

The aim of this study is to establish a binary logistic regression method to evaluate and select cucumber cultivars (Cucumis sativus L.) with a longer postharvest shelf life. Each sample was evaluated for commercial quality (fruit aging, weight loss, wilting, yellowing, chilling injury, and rotting) every 7 days of storage. Simple and multiple binary logistic regression models were applied in which the dependent variable was the probability of marketability and the independent variables were the days of storage, cultivars, fruit weight loss, and months of evaluation. The results showed that cucumber cultivars with a longer shelf life can be selected by a simple and multiple binary logistic regression analysis. Storage time was the main determinant of fruit marketability. Fruit weight loss strongly influenced the probability of marketability. The logistic model allowed us to determine the cucumber weight loss percentage over which a fruit would be rejected in the market.


2019 ◽  
Vol 23 (9) ◽  
pp. 3765-3786 ◽  
Author(s):  
Keith S. Jennings ◽  
Noah P. Molotch

Abstract. A critical component of hydrologic modeling in cold and temperate regions is partitioning precipitation into snow and rain, yet little is known about how uncertainty in precipitation phase propagates into variability in simulated snow accumulation and melt. Given the wide variety of methods for distinguishing between snow and rain, it is imperative to evaluate the sensitivity of snowpack model output to precipitation phase determination methods, especially considering the potential of snow-to-rain shifts associated with climate warming to fundamentally change the hydrology of snow-dominated areas. To address these needs we quantified the sensitivity of simulated snow accumulation and melt to rain–snow partitioning methods at sites in the western United States using the SNOWPACK model without the canopy module activated. The methods in this study included different permutations of air, wet bulb and dew point temperature thresholds, air temperature ranges, and binary logistic regression models. Compared to observations of snow depth and snow water equivalent (SWE), the binary logistic regression models produced the lowest mean biases, while high and low air temperature thresholds tended to overpredict and underpredict snow accumulation, respectively. Relative differences between the minimum and maximum annual snowfall fractions predicted by the different methods sometimes exceeded 100 % at elevations less than 2000 m in the Oregon Cascades and California's Sierra Nevada. This led to ranges in annual peak SWE typically greater than 200 mm, exceeding 400 mm in certain years. At the warmer sites, ranges in snowmelt timing predicted by the different methods were generally larger than 2 weeks, while ranges in snow cover duration approached 1 month and greater. Conversely, the three coldest sites in this work were relatively insensitive to the choice of a precipitation phase method, with average ranges in annual snowfall fraction, peak SWE, snowmelt timing, and snow cover duration of less than 18 %, 62 mm, 10 d, and 15 d, respectively. Average ranges in snowmelt rate were typically less than 4 mm d−1 and exhibited a small relationship to seasonal climate. Overall, sites with a greater proportion of precipitation falling at air temperatures between 0 and 4 ∘C exhibited the greatest sensitivity to method selection, suggesting that the identification and use of an optimal precipitation phase method is most important at the warmer fringes of the seasonal snow zone.


Author(s):  
E. Keith Smith ◽  
Michael G. Lacy ◽  
Adam Mayer

Standard mediation techniques for fitting mediation models cannot readily be translated to nonlinear regression models because of scaling issues. Methods to assess mediation in regression models with categorical and limited response variables have expanded in recent years, and these techniques vary in their approach and versatility. The recently developed khb technique purports to solve the scaling problem and produce valid estimates across a range of nonlinear regression models. Prior studies demonstrate that khb performs well in binary logistic regression models, but performance in other models has yet to be investigated. In this article, we evaluate khb‘s performance in fitting ordinal logistic regression models as an exemplar of the wider set of models to which it applies. We examined performance across 38,400 experimental conditions involving sample size, number of response categories, distribution of variables, and amount of mediation. Results indicate that under all experimental conditions, khb estimates the difference (mediation) coefficient and its associated standard error with little bias and that the nominal confidence interval coverage closely matches the actual. Our results suggest that researchers using khb can assume that the routine reasonably approximates population parameters.


Author(s):  
Rik Ossenkoppele ◽  
◽  
Antoine Leuzy ◽  
Hanna Cho ◽  
Carole H. Sudre ◽  
...  

Abstract Purpose A substantial proportion of amyloid-β (Aβ)+ patients with clinically diagnosed Alzheimer’s disease (AD) dementia and mild cognitive impairment (MCI) are tau PET–negative, while some clinically diagnosed non-AD neurodegenerative disorder (non-AD) patients or cognitively unimpaired (CU) subjects are tau PET–positive. We investigated which demographic, clinical, genetic, and imaging variables contributed to tau PET status. Methods We included 2338 participants (430 Aβ+ AD dementia, 381 Aβ+ MCI, 370 non-AD, and 1157 CU) who underwent [18F]flortaucipir (n = 1944) or [18F]RO948 (n = 719) PET. Tau PET positivity was determined in the entorhinal cortex, temporal meta-ROI, and Braak V-VI regions using previously established cutoffs. We performed bivariate binary logistic regression models with tau PET status (positive/negative) as dependent variable and age, sex, APOEε4, Aβ status (only in CU and non-AD analyses), MMSE, global white matter hyperintensities (WMH), and AD-signature cortical thickness as predictors. Additionally, we performed multivariable binary logistic regression models to account for all other predictors in the same model. Results Tau PET positivity in the temporal meta-ROI was 88.6% for AD dementia, 46.5% for MCI, 9.5% for non-AD, and 6.1% for CU. Among Aβ+ participants with AD dementia and MCI, lower age, MMSE score, and AD-signature cortical thickness showed the strongest associations with tau PET positivity. In non-AD and CU participants, presence of Aβ was the strongest predictor of a positive tau PET scan. Conclusion We identified several demographic, clinical, and neurobiological factors that are important to explain the variance in tau PET retention observed across the AD pathological continuum, non-AD neurodegenerative disorders, and cognitively unimpaired persons.


2014 ◽  
Vol 10 (2) ◽  
pp. 90-99 ◽  
Author(s):  
Darcy White ◽  
Rob Stephenson

As the rate of HIV infection continues to rise among men who have sex with men (MSM) in the United States, a focus of current prevention efforts is to encourage frequent HIV testing. Although levels of lifetime testing are high, low levels of routine testing among MSM are concerning. Using data from an online sample of 768 MSM, this article explores how perceptions of HIV prevalence are associated with HIV testing behavior. Ordinal logistic regression models were fitted to examine correlates of perceived prevalence, and binary logistic regression models were fitted to assess associations between perceived prevalence and HIV testing. The results indicate that perceptions of higher prevalence among more proximal reference groups such as friends and sex partners are associated with greater odds of HIV testing. Perceptions of HIV prevalence were nonuniform across the sample; these variations point to groups to target with strategic messaging and interventions to increase HIV testing among MSM.


Sign in / Sign up

Export Citation Format

Share Document