Asymptotic normality of the posterior in relative entropy

Bertrand S. Clarke

Research output: Contribution to journalArticle

13 Scopus citations

Abstract

We show that the relative entropy between a posterior density formed from a smooth likelihood and prior and a limiting normal form tends to zero in the independent and identically distributed case. The mode of convergence is in probability and in mean. Applications to codelengths in stochastic complexity and to sample size selection are briefly discussed.

Original languageEnglish (US)
Pages (from-to)165-176
Number of pages12
JournalIEEE Transactions on Information Theory
Volume45
Issue number1
DOIs
Publication statusPublished - Dec 1 1999

    Fingerprint

Keywords

  • Asymptotic normality
  • Posterior density
  • Relative entropy

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Cite this