负二项分布可靠度的E-Bayes估计  

E-Bayesian Estimation of the Negative Binomial Distribution Reliability

作　　者：苏清华[1,2] 胡中波[1] 

机构地区：[1]孝感学院数学与统计学院,湖北孝感432000 [2]武汉理工大学理学院,湖北武汉430074

出　　处：《湖北民族学院学报（自然科学版）》2011年第2期129-132,170,共5页Journal of Hubei Minzu University(Natural Science Edition)

基　　金：湖北省教育厅优秀中青年人才项目(Q20102705)

摘　　要：对负二项分布,给出在熵损失函数下当可靠度的先验分布为Beta分布和幂分布时可靠度的Bayes估计、E-Bayes估计及多层Bayes估计,并针对先验分布为幂分布的情形设计了相应的数值实验.实验结果表明,相对于负二项分布可靠度的多层Bayes估计,其E-Bayes估计的计算更简单,且稳健性也更好.In this paper,under entropy loss function,the Bayesian estimation,the E-Bayesian estimation and hierarchical Bayesian estimation of the negative binomial distribution reliability θ with the Beta distribution and the power distribution as its prior distribution are given.The numerical results show that the E-Bayesian estimation of θ with the power distribution as its prior distribution is more robust and easier to calculate than its hierarchical Bayesian estimation.

关 键 词：负二项分布 熵损失函数 E-BAYES估计 多层BAYES估计 

分 类 号：O213.2[理学—概率论与数理统计]