The Bernstein–von Mises theorem and nonregular models
Open Access
- 1 October 2014
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 42 (5) , 1850-1878
Abstract
We study the asymptotic behaviour of the posterior distribution in a broad class of statistical models where the “true” solution occurs on the boundary of the parameter space. We show that in this case Bayesian inference is consistent, and that the posterior distribution has not only Gaussian components as in the case of regular models (the Bernstein–von Mises theorem) but also has Gamma distribution components whose form depends on the behaviour of the prior distribution near the boundary and have a faster rate of convergence. We also demonstrate a remarkable property of Bayesian inference, that for some models, there appears to be no bound on efficiency of estimating the unknown parameter if it is on the boundary of the parameter space. We illustrate the results on a problem from emission tomography.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Parametric estimation. Finite sample theoryThe Annals of Statistics, 2012
- Consistency of the maximum likelihood estimator for general hidden Markov modelsThe Annals of Statistics, 2011
- Asymptotic Efficiency in Parametric Structural Models with Parameter-Dependent SupportEconometrica, 2003
- Asymptotic normality with small relative errors of posterior probabilities of half-spacesThe Annals of Statistics, 2002
- On the asymptotics of constrained local $M$-estimatorsThe Annals of Statistics, 2000
- Fully Bayesian Reconstructions from Single-Photon Emission Computed Tomography DataJournal of the American Statistical Association, 1997
- On convergence of posterior distributionsThe Annals of Statistics, 1995
- Laplace Approximations for Posterior Expectations When the Mode Occurs at the Boundary of the Parameter SpaceJournal of the American Statistical Association, 1994
- Speed of Estimation in Positron Emission Tomography and Related Inverse ProblemsThe Annals of Statistics, 1990
- Asymptotic Properties of Maximum Likelihood Estimators and Likelihood Ratio Tests under Nonstandard ConditionsJournal of the American Statistical Association, 1987