NA样本下Weibull分布族参数的经验贝叶斯估计  

Empirical Bayes Estimation for Parameters of Weibull Distribution Family Using NA Samples

作　　者：李星亚[1] 师义民[1] 李豪亮[1] 

机构地区：[1]西北工业大学应用数学系,陕西西安710129

出　　处：《昆明理工大学学报（理工版）》2009年第2期116-121,共6页Journal of Kunming University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金(项目编号:70471057)

摘　　要：在NA样本下研究W eibull分布参数的经验Bayes估计.利用核估计方法构造了参数的经验Bayes估计,在平方损失下获得了该估计的收敛速度,并证明了收敛速度的阶可以任意接近于1/2.最后给出例子,说明了定理条件的合理性.The empirical Bayes estimation for the parameters of Weibull distribution family using NA samples is studied in this paper. The EB estimation for the parameters is constructed by the method of kernel estimation. The convergence rates of the EB estimation are obtained under the squared loss. With some suitable conditions, the rank of convergence rates for the EB estimation is shown arbitrarily approaching to 1/2. One example is finally given to show the rationality of the conditions in the theorem.

关 键 词：NA样本 经验BAYES估计 收敛速度 

分 类 号：O212.1[理学—概率论与数理统计]