Bayesian model selection for generalized linear mixed models.

Autor: Xu S; Department of Statistics, Virginia Tech, Blacksburg, Virginia, USA., Ferreira MAR; Department of Statistics, Virginia Tech, Blacksburg, Virginia, USA., Porter EM; Department of Statistics, Virginia Tech, Blacksburg, Virginia, USA., Franck CT; Department of Statistics, Virginia Tech, Blacksburg, Virginia, USA.
Jazyk: angličtina
Zdroj: Biometrics [Biometrics] 2023 Dec; Vol. 79 (4), pp. 3266-3278. Date of Electronic Publication: 2023 Jun 27.
DOI: 10.1111/biom.13896
Abstrakt: We propose a Bayesian model selection approach for generalized linear mixed models (GLMMs). We consider covariance structures for the random effects that are widely used in areas such as longitudinal studies, genome-wide association studies, and spatial statistics. Since the random effects cannot be integrated out of GLMMs analytically, we approximate the integrated likelihood function using a pseudo-likelihood approach. Our Bayesian approach assumes a flat prior for the fixed effects and includes both approximate reference prior and half-Cauchy prior choices for the variances of random effects. Since the flat prior on the fixed effects is improper, we develop a fractional Bayes factor approach to obtain posterior probabilities of the several competing models. Simulation studies with Poisson GLMMs with spatial random effects and overdispersion random effects show that our approach performs favorably when compared to widely used competing Bayesian methods including deviance information criterion and Watanabe-Akaike information criterion. We illustrate the usefulness and flexibility of our approach with three case studies including a Poisson longitudinal model, a Poisson spatial model, and a logistic mixed model. Our proposed approach is implemented in the R package GLMMselect that is available on CRAN.
(© 2023 The Authors. Biometrics published by Wiley Periodicals LLC on behalf of International Biometric Society.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje