Decemeber 2006
Maybe the main difficulty for objective Bayesian hypothesis testing (and model selection in general), is that usual objective improper priors can not be used for parameters not occurring in all of the models. In this paper we introduce (objective) proper prior distributions for hypothesis testing and model selection based on measures of divergence between the competing models; we call them {\it divergence based} (DB) priors . DB priors have simple forms and desirable properties, like information (finite sample) consistency; often, they are similar to other existing proposals like the intrinsic priors; moreover, in normal linear models scenarios, they exactly reproduce Jeffreys-Zellner-Siow priors. Most importantly, in challenging scenarios such as irregular models and mixture models, the DB priors are well defined and very reasonable, while alternative proposals are not. We derive approximations to the DB priors as well as MCMC and asymptotic expressions for the associated Bayes factors, which also reveals interesting connections with other proposals (like the unit information priors).
Keywords: Bayes factors; Intrinsic priors; Jeffreys-Zellner-Siow priors; Symmetric Kullback-Leibler divergence; Unit information priors.
The manuscript is available in PDF format.