Open Access
April 2003 Adaptive Bayesian inference on the mean of an infinite-dimensional normal distribution
Eduard Belitser, Subhashis Ghosal
Ann. Statist. 31(2): 536-559 (April 2003). DOI: 10.1214/aos/1051027880


We consider the problem of estimating the mean of an infinite-break dimensional normal distribution from the Bayesian perspective. Under the assumption that the unknown true mean satisfies a "smoothness condition," we first derive the convergence rate of the posterior distribution for a prior that is the infinite product of certain normal distributions and compare with the minimax rate of convergence for point estimators. Although the posterior distribution can achieve the optimal rate of convergence, the required prior depends on a "smoothness parameter" q. When this parameter q is unknown, besides the estimation of the mean, we encounter the problem of selecting a model. In a Bayesian approach, this uncertainty in the model selection can be handled simply by further putting a prior on the index of the model. We show that if q takes values only in a discrete set, the resulting hierarchical prior leads to the same convergence rate of the posterior as if we had a single model. A slightly weaker result is presented when q is unrestricted. An adaptive point estimator based on the posterior distribution is also constructed.


Download Citation

Eduard Belitser. Subhashis Ghosal. "Adaptive Bayesian inference on the mean of an infinite-dimensional normal distribution." Ann. Statist. 31 (2) 536 - 559, April 2003.


Published: April 2003
First available in Project Euclid: 22 April 2003

zbMATH: 1039.62039
MathSciNet: MR1983541
Digital Object Identifier: 10.1214/aos/1051027880

Primary: 62G20
Secondary: 62C10 , 62G05

Keywords: Adaptive Bayes procedure , convergence rate , minimax risk , Model selection , posterior distribution

Rights: Copyright © 2003 Institute of Mathematical Statistics

Vol.31 • No. 2 • April 2003
Back to Top