New approaches to Bayesian consistency

2004/10/01 by Stephen G. Walker, Stephen Walker · 5 citations
Computer Science · Mathematics · #Bayesian Methods and Mixture Models #Bayesian Modeling and Causal Inference #Statistical Methods and Inference #math.ST #msc:62G20 #stat.TH

paper · pdf · doi:10.1214/009053604000000409

published as Annals of Statistics 2004, Vol. 32, No. 5, 2028-2043 · Published at http://dx.doi.org/10.1214/009053604000000409 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

openalex publication_date 2004/10/01 · arxiv created 2005/03/29 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We use martingales to study Bayesian consistency. We derive sufficient conditions for both Hellinger and Kullback–Leibler consistency, which do not rely on the use of a sieve. Alternative sufficient conditions for Hellinger consistency are also found and demonstrated on examples.

Cited by

• Consistency of Bayes estimators of a binary regression function
• Prediction Markets as Bayesian Inverse Problems: Uncertainty Quantification, Identifiability, and Information Gain from Price-Volume Histories under Latent Types
• Posterior asymptotics in Wasserstein metrics on the real line
• On the geometry of weak convergence without total variation convergence
• Some Simple Formulas for Posterior Convergence Rates