Posterior and cross-validatory predictive checks: A comparison of MCMC and INLA

Leonhard Held, Birgit Schrödle, Håvard Rue

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

152 Scopus citations

Abstract

Model criticism and comparison of Bayesian hierarchical models is often based on posterior or leave-one-out cross-validatory predictive checks. Cross-validatory checks are usually preferred because posterior predictive checks are difficult to assess and tend to be too conservative. However, techniques for statistical inference in such models often try to avoid full (manual) leave-one-out cross-validation, since it is very time-consuming. In this paper we will compare two approaches for estimating Bayesian hierarchical models: Markov chain Monte Carlo (MCMC) and integrated nested Laplace approximations (INLA). We review how both approaches allow for the computation of leave-one-out cross-validatory checks without re-running the model for each observation in turn. We then empirically compare the two approaches in an extensive case study analysing the spatial distribution of bovine viral diarrhoe (BVD) among cows in Switzerland.

Original languageEnglish (US)
Title of host publicationStatistical Modelling and Regression Structures
Subtitle of host publicationFestschrift in Honour of Ludwig Fahrmeir
PublisherPhysica-Verlag HD
Pages91-110
Number of pages20
ISBN (Print)9783790824124
DOIs
StatePublished - 2010
Externally publishedYes

Keywords

  • Bayesian hierarchical models
  • INLA
  • Leave-one-out cross-validation
  • MCMC
  • Posterior predictive model checks

ASJC Scopus subject areas

  • General Mathematics

Fingerprint

Dive into the research topics of 'Posterior and cross-validatory predictive checks: A comparison of MCMC and INLA'. Together they form a unique fingerprint.

Cite this