On the Bernstein-von Mises Theorem with Infinite Dimensional Parameters

  title={On the Bernstein-von Mises Theorem with Infinite Dimensional Parameters},
  author={David Freedman},
If there are many independent, identically distributed observations governed by a smooth, finite-dimensional statistical model, the Bayes estimate and the maximum likelihood estimate will be close. Furthermore, the posterior distribution of the parameter vector around the posterior mean will be close to the distribution of the maximum likelihood estimate around truth. Thus, Bayesian confidence sets have good frequentist coverage properties, and conversely. However, even for the simplest… CONTINUE READING

From This Paper

Topics from this paper.
63 Citations
13 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 13 references

An analysis of Bayesian inference for nonparametric regression

  • D. Cox
  • Annals of Statistics
  • 1993
Highly Influential
10 Excerpts

On local uniformity for estimators and confidence limits. Technical report, Statistics Department, University of Cologne

  • J. Pfanzagl
  • 1998
1 Excerpt

Asymptotic equivalence of nonparametric regression and white noise

  • L. D. Brown, M. G. Low
  • Annals of Statistics
  • 1996
1 Excerpt

Nonexistence of informative unbiased estimators in singular problems

  • L. D. Brown, R. Liu
  • Annals of Statistics
  • 1993
2 Excerpts

Theory of Point Estimation

  • E. Lehmann
  • 1991
2 Excerpts

Asymptotics in Statistics: Some Basic Concepts

  • LeCam, M Lucien, Yang, Grace Lo
  • 1990

Asymptotic Theory of Statistical Inference

  • B.L.S. Prakasa Rao
  • 1987
2 Excerpts

Similar Papers

Loading similar papers…