Parameter estimation of Poisson generalized linear mixed models based on three different statistical principles: a simulation study
2015 (English)In: SORT - Statistics and Operations Research Transactions, ISSN 1696-2281, E-ISSN 2013-8830, Vol. 39, no 2, 281-308 p.Article in journal (Refereed) PublishedText
Generalized linear mixed models are flexible tools for modeling non-normal data and are useful for accommodating overdispersion in Poisson regression models with random effects. Their main difficulty resides in the parameter estimation because there is no analytic solution for the maximization of the marginal likelihood. Many methods have been proposed for this purpose and many of them are implemented in software packages. The purpose of this study is to compare the performance of three different statistical principles - marginal likelihood, extended likelihood, Bayesian analysis-via simulation studies. Real data on contact wrestling are used for illustration.
Place, publisher, year, edition, pages
2015. Vol. 39, no 2, 281-308 p.
Estimation methods, Overdispersion, Poisson generalized linear mixed models, Simulation study, Sport injuries, Statistical principles, Random processes, Regression analysis, Generalized linear mixed models, Simulation studies, Parameter estimation
Probability Theory and Statistics
Research subject Complex Systems – Microdata Analysis
IdentifiersURN: urn:nbn:se:du-20788ISI: 000368469900007ScopusID: 2-s2.0-84953393890OAI: oai:DiVA.org:du-20788DiVA: diva2:894632