BAYESIAN ROBUSTNESS FOR MULTIPARAMETER PROBLEMS

被引：7

作者：

DELAMPADY, M

DEY, DK

机构：

[1] INDIAN STAT INST,ECON ANAL UNIT,BANGALORE 560009,INDIA

[2] UNIV CONNECTICUT,DEPT STAT,STORRS,CT 06209

来源：

JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 1994年 / 40卷 / 2-3期

关键词：

PHI-DIVERGENCE; EPSILON-CONTAMINATION; CURVATURE;

D O I：

10.1016/0378-3758(94)90132-5

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：

Bayesian robustness is studied for epsilon-contamination classes of prior distributions. Nonparametric classes of contaminations such as the class of all unimodal spherically symmetric densities are considered here. Posterior phi-divergence and its curvature are used to measure the sensitivity of priors on the resulting posterior densities. Examples are provided to illustrate our results.

引用

页码：375 / 382

页数：8

共 6 条

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