A Bayes factor with reasonable model selection consistency for ANOVA model

Abstract

For the ANOVA model, we propose a new g-prior based Bayes factor without integral representation, with reasonable model selection consistency for any asymptotic situations (either number of levels of the factor and/or number of replication in each level goes to infinity). Exact analytic calculation of the marginal density under a special choice of the priors enables such a Bayes factor.