Open Access
VOL. 6 | 2010 Dilution priors: Compensating for model space redundancy
Edward I. George

Editor(s) James O. Berger, T. Tony Cai, Iain M. Johnstone

Inst. Math. Stat. (IMS) Collect., 2010: 158-165 (2010) DOI: 10.1214/10-IMSCOLL611


For the general Bayesian model uncertainty framework, the focus of this paper is on the development of model space priors which can compensate for redundancy between model classes, the so-called dilution priors proposed in George (1999). Several distinct approaches for dilution prior construction are suggested. One is based on tessellation determined neighborhoods, another on collinearity adjustments, and a third on pairwise distances between models.


Published: 1 January 2010
First available in Project Euclid: 26 October 2010

MathSciNet: MR2798517

Digital Object Identifier: 10.1214/10-IMSCOLL611

Primary: 62F15 , 62J05

Keywords: model averaging , Model selection , objective Bayes , prior distribution , Variable selection

Rights: Copyright © 2010, Institute of Mathematical Statistics

Back to Top