Fast and accurate Bayesian model criticism and conflict diagnostics using R-INLA

Abstract

Bayesian hierarchical models are increasingly popular for realistic modelling and analysis of complex data. This trend is accompanied by the need for flexible, general, and computationally efficient methods for model criticism and conflict detection. Usually, a Bayesian hierarchical model incorporates a grouping of the individual data points, for example individuals in repeated measurement data. In such cases, the following question arises: Are any of the groups "outliers", or in conflict with the remaining groups? Existing general approaches aiming to answer such questions tend to be extremely computationally demanding when model fitting is based on MCMC. We show how group-level model criticism and conflict detection can be done quickly and accurately through integrated nested Laplace approximations (INLA). The new method is implemented as a part of the open source R-INLA package for Bayesian computing (http://r-inla.org).

References in corpus (7)

• Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC
• Asymptotic Equivalence of Bayes Cross Validation and Widely Applicable Information Criterion in Singular Learning Theory
• Statistical applications of the multivariate skew-normal distribution
• Bayesian Checking of the Second Levels of Hierarchical Models
• Improving the INLA approach for approximate Bayesian inference for latent Gaussian models
• Conflict Diagnostics in Directed Acyclic Graphs, with Applications in Bayesian Evidence Synthesis
• Conflict diagnostics for evidence synthesis in a multiple testing framework

Cited by in corpus (2)

• Reverse-Bayes methods for evidence assessment and research synthesis
• The SPDE approach for Gaussian and non-Gaussian fields: 10 years and still running