ROBUST BAYESIAN-ANALYSIS USING DIVERGENCE MEASURES

被引：51

作者：

DEY, DK ^{[1
]}

BIRMIWAL, LR ^{[1
]}

机构：

[1] UNIV CONNECTICUT,DEPT STAT,STORRS,CT 06269

来源：

STATISTICS & PROBABILITY LETTERS | 1994年 / 20卷 / 04期

关键词：

BAYESIAN ROBUSTNESS; CURVATURE; EPSILON-CONTAMINATION CLASSES OF PRIORS; GEOMETRIC CONTAMINATION PHI-DIVERGENCE MEASURES;

D O I：

10.1016/0167-7152(94)90016-7

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We consider the problem of measuring Bayesian robustness of classes of contaminated priors. Two classes of priors in the neighborhood of the elicited prior are considered, one is the usual epsilon-contaminated class and the other one is a geometric mixing class. A global measure, using phi-divergence of the posterior distributions and its curvature, is introduced. Calculation of ranges of the curvatures are demonstrated through examples. It is shown that the curvature formulas give unified answers irrespective of the choice of the phi-functions. It is also observed that the variation of the posterior divergence measures and their curvature are especially useful for multidimensional problems.

引用

页码：287 / 294

页数：8

共 24 条

[1]

ATKINSON AC, 1970, J ROY STAT SOC B, V32, P323

[2] ROBUST BAYES AND EMPIRICAL BAYES ANALYSIS WITH EPSILON-CONTAMINATED PRIORS [J].