Bayesian Model Selection Based on Proper Scoring Rules
Statistics Theory
2020-04-28 v2 Statistics Theory
Abstract
Bayesian model selection with improper priors is not well-defined because of the dependence of the marginal likelihood on the arbitrary scaling constants of the within-model prior densities. We show how this problem can be evaded by replacing marginal log-likelihood by a homogeneous proper scoring rule, which is insensitive to the scaling constants. Suitably applied, this will typically enable consistent selection of the true model.
Cite
@article{arxiv.1409.5291,
title = {Bayesian Model Selection Based on Proper Scoring Rules},
author = {A. Philip Dawid and Monica Musio},
journal= {arXiv preprint arXiv:1409.5291},
year = {2020}
}
Comments
Published at http://dx.doi.org/10.1214/15-BA942 in the Bayesian Analysis (http://projecteuclid.org/euclid.ba) by the International Society of Bayesian Analysis (http://bayesian.org/)