English

A Bayes factor with reasonable model selection consistency for ANOVA model

Methodology 2012-06-14 v2

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.

Keywords

Cite

@article{arxiv.0906.4329,
  title  = {A Bayes factor with reasonable model selection consistency for ANOVA model},
  author = {Yuzo Maruyama},
  journal= {arXiv preprint arXiv:0906.4329},
  year   = {2012}
}

Comments

a major revision

R2 v1 2026-06-21T13:17:04.154Z