两两NQD序列下非指数分布族参数的经验Bayes检验  

Empirical Bayes Test of Parameter for a Non-exponential Distribution Family with NQD Random Series in Twos

作　　者：邵敏娜[1] 

机构地区：[1]宁夏大学数学计算机学院,银川750021

出　　处：《西南师范大学学报（自然科学版）》2014年第11期30-34,共5页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：宁夏大学科学研究基金资助项目(ZR1214)

摘　　要：讨论两两NQD序列下非指数分布族参数的经验Bayes(EB)检验问题.利用概率密度函数的核估计方法,构造参数的EB检验函数,在适当的条件下证明EB检验函数是渐近最优的,并获得了它的收敛速度.最后举出一个满足定理条件的例子.The empirical Bayes （EB） test problem has been investigated in this paper for the parameter of a non‐exponential distribution family with NQD random series in twos .By means of the kernel‐type density estimation method ,the EB test decision rules of the parameter have been constructed ,which proves the asymptotically optimal property and convergence rates for the EB test decision rules under some suitable conditions .Finally ,an example satisfying the conditions of theorem has been given .

关 键 词：两两NQD序列 核估计 经验BAYES检验 收敛速度 非指数分布 

分 类 号：O212.1[理学—概率论与数理统计]