DocumentCode
1474635
Title
Asymptotic normality of the posterior in relative entropy
Author
Clarke, Bertrand S.
Author_Institution
Dept. of Statistics, British Columbia Univ., Vancouver, BC, Canada
Volume
45
Issue
1
fYear
1999
fDate
1/1/1999 12:00:00 AM
Firstpage
165
Lastpage
176
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 code lengths in stochastic complexity and to sample size selection are discussed
Keywords
codes; computational complexity; convergence of numerical methods; entropy; probability; signal sampling; asymptotic normality; code lengths; convergence; i.i.d. case; limiting normal form; mean; posterior density; probability; relative entropy; sample size selection; smooth likelihood; stochastic complexity; Bayesian methods; Convergence; Density measurement; Entropy; Maximum likelihood estimation; Parameter estimation; Size measurement; Source coding; Statistics; Stochastic processes;
fLanguage
English
Journal_Title
Information Theory, IEEE Transactions on
Publisher
ieee
ISSN
0018-9448
Type
jour
DOI
10.1109/18.746784
Filename
746784
Link To Document