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

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.