A Bayesian Information Criterion for Singular Models

Citations Over TimeTop 10% of 2017 papers

Abstract

Summary We consider approximate Bayesian model choice for model selection problems that involve models whose Fisher information matrices may fail to be invertible along other competing submodels. Such singular models do not obey the regularity conditions underlying the derivation of Schwarz's Bayesian information criterion BIC and the penalty structure in BIC generally does not reflect the frequentist large sample behaviour of the marginal likelihood. Although large sample theory for the marginal likelihood of singular models has been developed recently, the resulting approximations depend on the true parameter value and lead to a paradox of circular reasoning. Guided by examples such as determining the number of components in mixture models, the number of factors in latent factor models or the rank in reduced rank regression, we propose a resolution to this paradox and give a practical extension of BIC for singular model selection problems.

Related Papers

• → Selecting Path Models in SEM: A Comparison of Model Selection Criteria(2017)121 cited
• → Comparison of Akaike information criterion (AIC) and Bayesian information criterion (BIC) in selection of an asymmetric price relationship(2010)109 cited
• → Information criteria: How do they behave in different models?(2013)77 cited
• → Bayesian Model Comparison and Model Checking(2012)
• → Are Information criteria good enough to choose the right the number of regimes in Hidden Markov Models?(2023)