随机删失下刻度参数的单调经验贝叶斯检验  

Monotone Empirical Bayes Test for Scale Parameter under Random Censorship

作　　者：王立春[1] 

机构地区：[1]北京交通大学理学院数学系,北京100044

出　　处：《应用概率统计》2007年第4期419-427,共9页Chinese Journal of Applied Probability and Statistics

基　　金：Partly supported by NNSF of China(No.10571001)

摘　　要：利用经验贝叶斯方法研究了刻度指数族的两行动问题,提出了一个在历史样本被随机右删失的条件下收敛速度可以任意接近O(n^(-1))的单调经验贝叶斯检验.We study the two-action problem in the scale-exponential family via the empirical Bayes （EB） approach and present a monotone EB test possessing a rate of convergence which can be arbitrarily close to O（n^-1） under the condition that the past samples are randomly censored from the right.

关 键 词：经验贝叶斯 随机删失 刻度指数族 

分 类 号：O212.1[理学—概率论与数理统计]