AVERAGING ENTROPY

被引：19

作者：

CAMPBELL, LL

机构：

[1] Department of Mathematics and Statistics, Queen's University, Kingston

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1995年 / 41卷 / 01期

基金：

加拿大自然科学与工程研究理事会;

关键词：

AVERAGE ENTROPY; NONINFORMATIVE PRIORS; DIFFERENTIAL GEOMETRY;

D O I：

10.1109/18.370086

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

It is pointed out that a uniform distribution on probability n-tuples is not necessarily the best distribution to use in calculating an average entropy. The noninformative prior of Bayesian statistics and certain distributions which arise in differential-geometry approaches to statistics are other candidates. The mean and variance of the entropy are calculated when probability n-tuples are distributed according to these distributions.

引用

页码：338 / 339

页数：2

共 8 条

[1]

ABRAMOWITZ M, 1965, HDB MATH FUNCTIONS, pCH6

[2]

Amari S., 1985, LECT NOTES STAT

[3]

[Anonymous], 2006, ELEM INF THEORY

[4]

Box G.E.P., 1992, BAYESIAN INFERENCE S

[5] THE RELATION BETWEEN INFORMATION-THEORY AND THE DIFFERENTIAL GEOMETRY APPROACH TO STATISTICS [J].

CAMPBELL, LL .

INFORMATION SCIENCES, 1985, 35 (03) :199-210

[6]

Cencov N.N., 1982, TRANSLATIONS MATH MO, V53

[7]

GUNTHER CG, 1993, 1993 P INT S INF THE, P70

[8]

Rao C. R., 1945, B CALCUTTA MATH SOC, V37, P81, DOI DOI 10.1007/978-1-4612-0919-5_15

← 1 →