期刊名称：Electronic Journal of Applied Statistical Analysis
电子版ISSN：2070-5948
出版年度：2018
卷号：11
期号：2
页码：622-654
DOI：10.1285/i20705948v11n2p622
语种：English
出版社：University of Salento
其他摘要：We present an approximate posterior inference methodology for a Bayesian hierarchical mixed-effect Poisson regression model. The model serves us to address the multiple testing problem in the presence of many group or cluster effects. This is carried out through a specialized Bayesian false discovery rate procedure. The likelihood is simplified by an approximation based on Laplace's approximation for integrals and a trace approximation for the determinants. The posterior marginals are estimated using this approximated likelihood. In particular, we obtain credible regions for the parameters, as well as probability estimates for the difference between risks (Poisson intensities) associated with different groups or clusters, or different levels of the fixed effects. The methodology is illustrated through an application to a vaccine trial.
