Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns

In logistic regression, before concluding that the model fits well, it is crucial that other measures be examined to see if goodness-of-fit is supported over the entire set of covariate patterns. This is accomplished through a series of specialized measures known as logistic regression diagnostics....

Full description

Bibliographic Details
Main Authors: Sarkar, S. K., Midi, Habshah, Rahmatullah Imon, A. H. M.
Format: Article
Published: Academic Publications 2010
Online Access:http://psasir.upm.edu.my/id/eprint/14041/
_version_ 1848842283217059840
author Sarkar, S. K.
Midi, Habshah
Rahmatullah Imon, A. H. M.
author_facet Sarkar, S. K.
Midi, Habshah
Rahmatullah Imon, A. H. M.
author_sort Sarkar, S. K.
building UPM Institutional Repository
collection Online Access
description In logistic regression, before concluding that the model fits well, it is crucial that other measures be examined to see if goodness-of-fit is supported over the entire set of covariate patterns. This is accomplished through a series of specialized measures known as logistic regression diagnostics. In this study, one-step approximation diagnostics for logistic regression are computed on the basis of individual subjects as well as covariate patterns. The plots suggest that the outliers and influential observations are more clearly visualized and detected whether the diagnostics are computed on the basis of covariate patterns than individual subjects. So, diagnostic statistics should be computed taking into account covariate patterns specially when the number of covariate patterns is much smaller than the sample size and the number of subjects within any covariate patterns is larger than five. Finally, it may be concluded that one should not proceed to presenting the results from a fitted logistic regression model until the fit of the model has been thoroughly assessed using both summary measures and diagnostic statistics. The diagnostic statistics should be computed on the basis of covariate patterns, if necessary.
first_indexed 2025-11-15T07:56:40Z
format Article
id upm-14041
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T07:56:40Z
publishDate 2010
publisher Academic Publications
recordtype eprints
repository_type Digital Repository
spelling upm-140412015-06-18T06:09:34Z http://psasir.upm.edu.my/id/eprint/14041/ Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns Sarkar, S. K. Midi, Habshah Rahmatullah Imon, A. H. M. In logistic regression, before concluding that the model fits well, it is crucial that other measures be examined to see if goodness-of-fit is supported over the entire set of covariate patterns. This is accomplished through a series of specialized measures known as logistic regression diagnostics. In this study, one-step approximation diagnostics for logistic regression are computed on the basis of individual subjects as well as covariate patterns. The plots suggest that the outliers and influential observations are more clearly visualized and detected whether the diagnostics are computed on the basis of covariate patterns than individual subjects. So, diagnostic statistics should be computed taking into account covariate patterns specially when the number of covariate patterns is much smaller than the sample size and the number of subjects within any covariate patterns is larger than five. Finally, it may be concluded that one should not proceed to presenting the results from a fitted logistic regression model until the fit of the model has been thoroughly assessed using both summary measures and diagnostic statistics. The diagnostic statistics should be computed on the basis of covariate patterns, if necessary. Academic Publications 2010 Article PeerReviewed Sarkar, S. K. and Midi, Habshah and Rahmatullah Imon, A. H. M. (2010) Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns. International Journal of Applied Mathematics, 23 (1). pp. 63-81. ISSN 1311-1728 http://www.diogenes.bg/ijam/
spellingShingle Sarkar, S. K.
Midi, Habshah
Rahmatullah Imon, A. H. M.
Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns
title Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns
title_full Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns
title_fullStr Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns
title_full_unstemmed Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns
title_short Diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns
title_sort diagnostics of fitted binary logistic regression model based on individual subjects and covariate patterns
url http://psasir.upm.edu.my/id/eprint/14041/
http://psasir.upm.edu.my/id/eprint/14041/