Predictive Bayesian Model Selection

2011/01/01 by Tomohiro Ando · 2 citations
Mathematics · Computer Science · #Statistical Methods and Inference #Bayesian Methods and Mixture Models #Statistical Methods and Bayesian Inference #Bayesian probability #Model selection #Selection (genetic algorithm) #Computer science #Statistics #Machine learning #Artificial intelligence #Mathematics

paper · doi:10.1080/01966324.2011.10737798

openalex publication_date 2011/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

SYNOPTIC ABSTRACTWe investigate the problem of evaluating the goodness of the predictive distributions of Bayesian models. Recently, deviance information criteria (DIC) has been extensively employed in various study areas to evaluate the Bayesian models, thanks to its simplicity of calculation from the posterior simulation outputs. Unfortunately, it is known that DIC often selects overfitted models. In this paper, we develop a new criterion which can be calculated easily from posterior outputs under the model misspecification situation. The proposed criterion is developed as an estimator of the posterior mean of the expected likelihood and is robust to improper priors. Monte Carlo simulations are conducted to investigate the properties of the proposed criteria.

Citations

• Fractional Bayes Factors for Model Comparison
• Bayesian predictive information criterion for the evaluation of hierarchical Bayesian and empirical Bayes models
• Bayesian Measures of Model Complexity and Fit
• A new look at the statistical model identification
• Bayes Factors

Cited by

• The Deviance Information Criterion: 12 Years on
• Deviance information criterion [wikipedia]

Related

• Posterior Averaging Information Criterion
• On the large-sample limits of some Bayesian model evaluation statistics
• Deviance Information Criteria for Model Selection in Approximate Bayesian Computation
• Understanding predictive information criteria for Bayesian models
• Bayesian Model Selection for Misspecified Models in Linear Regression