中文摘要：

Bayes统计推断中的一个重要问题是它的稳健性．一般采用的后验稳健性的评价标准是使用传统的Bayes风险准则．1973年Huber给出的定理，对后验稳健性的计算是基于先验的ε-代换类D选所有分布的前提，但若D的选择太大会影响后验稳健性的效果．本文考虑用共轭分布法选取D，得到的后验稳健性比D取所有分布时要好．

英文摘要：

An important problem of Bayes statistic conclusion is Posterior Robustness. The judgemental standard of Robustness is the traditional Bayes risk rule. Huber gave a thesis in 1973, in which he discussed the Robustness of a on the base of D= {all distributions}. However, the range of D= {all distributions} is big that impact on the result of Robustness. So in this text, we select D by using the conjugate distribution method, and we get a better Posterior Robustness.