双边定数截尾情形下一个两参数有浴盆形状失效率的寿命分布参数的Bayes估计  

Bayesian Estimation for the Two-parameter Bathtub-shaped Lifetime Distribution Under Double Type-Ⅱ Censored Sample

作　　者：田霆[1] 刘次华[2] 陈家清[3] 

机构地区：[1]国立华侨大学数学科学学院,泉州362021 [2]华中科技大学数学与统计学院,武汉430074 [3]武汉理工大学理学院,武汉430063

出　　处：《武汉理工大学学报（交通科学与工程版）》2012年第5期1088-1090,1094,共4页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：福建省科研基金项目资助(批准号:Z0511027)

摘　　要：在双边定数截尾情形下,给出了一个2参数有浴盆形状失效率的寿命分布参数的极大似然估计和在平方损失下基于无信息先验下和共轭先验信息下的Bayes估计,通过大量的Monte-Carlo数值模拟试验,对这2种情况下的估计的结果与极大似然估计作了比较.当样本n较大时,r愈大,s愈小,即丢失数据的数目愈小,Γ先验的Bayes估计与极大似然估计差不多,更接近于真值,都比无先验的Bayes估计要好.When product life time follows the two-parameter bathtub-shaped life distribution,this arti- cle provide the maximum likelihood estimation and the Bayes estimation considering squared loss based on the non-informative prior and conjugate prior for the parameter under double type-II Censored sam- ple. Moreover, these estimators are compared with the maximum likelihood estimation by the Monte- Carlo simulation. When the sample size n is more greater, r is more biggers, is more smaller. Namely, the number of missing data is more smaller. The Bayes estimation of r prior is as much as the MLE, is close to the true data. They are more precision than the Bayes estimation of non-informative prior.

关 键 词：浴盆形状:失效率 极大似然估计 先验分布 平方损失 BAYES估计 

分 类 号：O213.2[理学—概率论与数理统计]