文章基本信息

标题：Intuitive Joint Priors for Variance Parameters
本地全文：下载
作者：Geir-Arne Fuglstad ; Ingeborg Gullikstad Hem ; Alexander Knight 等
期刊名称：Bayesian Analysis
印刷版ISSN：1931-6690
电子版ISSN：1936-0975
出版年度：2020
卷号：15
期号：4
页码：1109-1137
DOI：10.1214/19-BA1185
语种：English
出版社：International Society for Bayesian Analysis
摘要：Variance parameters in additive models are typically assigned independent priors that do not account for model structure. We present a new framework for prior selection based on a hierarchical decomposition of the total variance along a tree structure to the individual model components. For each split in the tree, an analyst may be ignorant or have a sound intuition on how to attribute variance to the branches. In the former case a Dirichlet prior is appropriate to use, while in the latter case a penalised complexity (PC) prior provides robust shrinkage. A bottom-up combination of the conditional priors results in a proper joint prior. We suggest default values for the hyperparameters and offer intuitive statements for eliciting the hyperparameters based on expert knowledge. The prior framework is applicable for R packages for Bayesian inference such as INLA and RStan.
关键词：additive models;hierarchical variance decomposition;latent Gaussian models;penalised complexity;joint prior distributions;variance parameters