负相伴样本情形连续型单参数指数族参数的经验Bayes检验问题  

The empirical Bayes test problem for continuous one-parameter exponential family in the case of negatively associated samples

作　　者：陈家清[1] 刘次华[2] 

机构地区：[1]武汉理工大学统计学系,湖北武汉430063 [2]华中科技大学数学系,湖北武汉430074

出　　处：《纯粹数学与应用数学》2007年第1期11-16,共6页Pure and Applied Mathematics

基　　金：国家自然科学基金资助项目(10301011)

摘　　要：在加权“线性损失”下讨论了负相伴样本情形连续型单参数指数族参数的经验Bayes(EB)检验问题.利用概率密度函数的核估计构造了参数的经验Bayes检验函数,并获得了它的渐近最优(a.o.)性,在适当的条件下证明了所提出的经验Bayes检验函数的收敛速度可任意接近O(-n 1/2).By using the kernel-type density estimation in the case of identically distributed and negatively associated samples, the empirical Bayes test rules for the continuous one-parameter exponential family are constructed under weighed linear loss function, and the asymptotically optimal property is obtained. It is shown that the convergence rates of the proposed EB test rules can arbitrarily close to O（n^-1/2） under suitable conditions.

关 键 词：经验BAYES检验 渐近最优性 收敛速度 负相伴样本 

分 类 号：O212.1[理学—概率论与数理统计]