Year: 2015
Type: article
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.
Source: Bayesian Analysis
DOI: 10.1214/15-ba942
Authors: A. Philip Dawid, Monica Musio
Institutions: University of Cambridge, University of Cagliari
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W2091940547