A Bayesian approach to analyse overdispersed longitudinal count data. Issue 11 (17th August 2016)

• Record Type: Journal Article
• Authors: Rizzato, Fernanda B.; Leandro, Roseli A.; Demétrio, Clarice G.B.; Molenberghs, Geert
• Is Part Of: Journal of applied statistics. Volume 43:Issue 11(2016)
• Page Start: 2085
• Page End: 2109
• Publication Date: 2016-08-17
• Subjects: Bayesian analysis -- Bayesian model assessment -- count data -- generalized linear mixed model -- over dispersion; Statistics -- Periodicals; 519.5
• DOI: 10.1080/02664763.2015.1126812
• Languages: English
• ISSNs: 0266-4763

Abstract

ABSTRACT: In this paper, we consider a model for repeated count data, with within-subject correlation and/or overdispersion. It extends both the generalized linear mixed model and the negative-binomial model. This model, proposed in a likelihood context [17, 18 ] is placed in a Bayesian inferential framework. An important contribution takes the form of Bayesian model assessment based on pivotal quantities, rather than the often less adequate DIC. By means of a real biological data set, we also discuss some Bayesian model selection aspects, using a pivotal quantity proposed by Johnson [12 ].