The formal definition of reference priors

2009/04/01 by James O. Berger, José M. Bernardo, Dongchu Sun · 1 citation
Mathematics · #math.ST #stat.TH #msc:62F15 #msc:62A01 #msc:62B10

paper · pdf · doi:10.1214/07-aos587

published as Annals of Statistics 2009, Vol. 37, No. 2, 905-938 · Published in at http://dx.doi.org/10.1214/07-AOS587 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

arxiv created 2009/04/01 · arxiv updated 2009/12/01

Abstract

Reference analysis produces objective Bayesian inference, in the sense that inferential statements depend only on the assumed model and the available data, and the prior distribution used to make an inference is least informative in a certain information-theoretic sense. Reference priors have been rigorously defined in specific contexts and heuristically defined in general, but a rigorous general definition has been lacking. We produce a rigorous general definition here and then show how an explicit expression for the reference prior can be obtained under very weak regularity conditions. The explicit expression can be used to derive new reference priors both analytically and numerically.

Cited by

• Cosmology as Representation: Informational Invariance and the Limits of Scientific Realism

Related

• Properly constrained reference priors decay rates for efficient and robust posterior inference
• The prior can generally only be understood in the context of the likelihood
• Learning Approximately Objective Priors
• Generalized mutual information and their reference priors under Csizar f-divergence
• An objective prior that unifies objective Bayes and information-based inference