Cargando…
Sample size issues in multilevel logistic regression models
Educational researchers, psychologists, social, epidemiological and medical scientists are often dealing with multilevel data. Sometimes, the response variable in multilevel data is categorical in nature and needs to be analyzed through Multilevel Logistic Regression Models. The main theme of this p...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874355/ https://www.ncbi.nlm.nih.gov/pubmed/31756205 http://dx.doi.org/10.1371/journal.pone.0225427 |
_version_ | 1783472825000001536 |
---|---|
author | Ali, Amjad Ali, Sabz Khan, Sajjad Ahmad Khan, Dost Muhammad Abbas, Kamran Khalil, Alamgir Manzoor, Sadaf Khalil, Umair |
author_facet | Ali, Amjad Ali, Sabz Khan, Sajjad Ahmad Khan, Dost Muhammad Abbas, Kamran Khalil, Alamgir Manzoor, Sadaf Khalil, Umair |
author_sort | Ali, Amjad |
collection | PubMed |
description | Educational researchers, psychologists, social, epidemiological and medical scientists are often dealing with multilevel data. Sometimes, the response variable in multilevel data is categorical in nature and needs to be analyzed through Multilevel Logistic Regression Models. The main theme of this paper is to provide guidelines for the analysts to select an appropriate sample size while fitting multilevel logistic regression models for different threshold parameters and different estimation methods. Simulation studies have been performed to obtain optimum sample size for Penalized Quasi-likelihood (PQL) and Maximum Likelihood (ML) Methods of estimation. Our results suggest that Maximum Likelihood Method performs better than Penalized Quasi-likelihood Method and requires relatively small sample under chosen conditions. To achieve sufficient accuracy of fixed and random effects under ML method, we established ‘‘50/50” and ‘‘120/50” rule respectively. On the basis our findings, a ‘‘50/60” and ‘‘120/70” rules under PQL method of estimation have also been recommended. |
format | Online Article Text |
id | pubmed-6874355 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-68743552019-12-06 Sample size issues in multilevel logistic regression models Ali, Amjad Ali, Sabz Khan, Sajjad Ahmad Khan, Dost Muhammad Abbas, Kamran Khalil, Alamgir Manzoor, Sadaf Khalil, Umair PLoS One Research Article Educational researchers, psychologists, social, epidemiological and medical scientists are often dealing with multilevel data. Sometimes, the response variable in multilevel data is categorical in nature and needs to be analyzed through Multilevel Logistic Regression Models. The main theme of this paper is to provide guidelines for the analysts to select an appropriate sample size while fitting multilevel logistic regression models for different threshold parameters and different estimation methods. Simulation studies have been performed to obtain optimum sample size for Penalized Quasi-likelihood (PQL) and Maximum Likelihood (ML) Methods of estimation. Our results suggest that Maximum Likelihood Method performs better than Penalized Quasi-likelihood Method and requires relatively small sample under chosen conditions. To achieve sufficient accuracy of fixed and random effects under ML method, we established ‘‘50/50” and ‘‘120/50” rule respectively. On the basis our findings, a ‘‘50/60” and ‘‘120/70” rules under PQL method of estimation have also been recommended. Public Library of Science 2019-11-22 /pmc/articles/PMC6874355/ /pubmed/31756205 http://dx.doi.org/10.1371/journal.pone.0225427 Text en © 2019 Ali et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Ali, Amjad Ali, Sabz Khan, Sajjad Ahmad Khan, Dost Muhammad Abbas, Kamran Khalil, Alamgir Manzoor, Sadaf Khalil, Umair Sample size issues in multilevel logistic regression models |
title | Sample size issues in multilevel logistic regression models |
title_full | Sample size issues in multilevel logistic regression models |
title_fullStr | Sample size issues in multilevel logistic regression models |
title_full_unstemmed | Sample size issues in multilevel logistic regression models |
title_short | Sample size issues in multilevel logistic regression models |
title_sort | sample size issues in multilevel logistic regression models |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6874355/ https://www.ncbi.nlm.nih.gov/pubmed/31756205 http://dx.doi.org/10.1371/journal.pone.0225427 |
work_keys_str_mv | AT aliamjad samplesizeissuesinmultilevellogisticregressionmodels AT alisabz samplesizeissuesinmultilevellogisticregressionmodels AT khansajjadahmad samplesizeissuesinmultilevellogisticregressionmodels AT khandostmuhammad samplesizeissuesinmultilevellogisticregressionmodels AT abbaskamran samplesizeissuesinmultilevellogisticregressionmodels AT khalilalamgir samplesizeissuesinmultilevellogisticregressionmodels AT manzoorsadaf samplesizeissuesinmultilevellogisticregressionmodels AT khalilumair samplesizeissuesinmultilevellogisticregressionmodels |