A comparative study on the performance of frequentist and Bayesian estimation methods under separation in logistic regression

dc.contributor.authorAltınışık, Yasin
dc.contributor.departmentOthertr_TR
dc.contributor.facultyOthertr_TR
dc.date.accessioned2021-11-22T09:06:42Z
dc.date.available2021-11-22T09:06:42Z
dc.date.issued2020-12-31
dc.description.abstractSeparation is one of the most commonly encountered estimation problems in the context of logistic regression, which often occurs with small and medium sample sizes. The method of maximum likelihood (MLE; Fisher) provides spuriously high parameter estimates and their standard errors under separation in logistic regression. Many researchers in social sciences utilize simple but ad-hoc solutions to overcome this issue, such as "doing nothing strategy", removing variable(s) from the model, and combining the levels of the categorical variable in the data causing separation etc. The limitations of these basic solutions have motivated researchers to use more appropriate and innovative estimation techniques to deal with the problem. However, the performance and comparison of these techniques have not been fully investigated yet. The main goal of this paper is to close this research gap by comparing the performance of frequentist and Bayesian estimation methods for coping with separation. A simulation study is performed to investigate the performance of asymptotic, bootstrap-based, and Bayesian estimation techniques with respect to bias, precision, and accuracy measures under separation. In line with the simulation study, a real-data example is used to illustrate how to utilize these methods to solve separation in logistic regression.tr_TR
dc.description.indexTrdizintr_TR
dc.identifier.endpage1103tr_TR
dc.identifier.issn/e-issn2618-6470
dc.identifier.issue2tr_TR
dc.identifier.startpage1083tr_TR
dc.identifier.urihttps://doi.org/10.31801/cfsuasmas.614492tr_TR
dc.identifier.urihttp://hdl.handle.net/20.500.12575/76196
dc.identifier.volume69tr_TR
dc.language.isoentr_TR
dc.publisherAnkara Üniversitesi Fen Fakültesitr_TR
dc.relation.isversionof10.31801/cfsuasmas.614492tr_TR
dc.relation.journalCommunications Faculty of Sciences University of Ankara Series A1 Mathematics and Statisticstr_TR
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Başka Kurum Yazarıtr_TR
dc.subjectLogistic regressiontr_TR
dc.subjectSeparation problemtr_TR
dc.subjectFrequentist and Bayesian estimationtr_TR
dc.titleA comparative study on the performance of frequentist and Bayesian estimation methods under separation in logistic regressiontr_TR
dc.typeArticletr_TR

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
8.pdf
Size:
1.34 MB
Format:
Adobe Portable Document Format
Description:
Dergi
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.62 KB
Format:
Item-specific license agreed upon to submission
Description: