分组数据的Bayes分析—Gibbs抽样方法

Bayes Ananlysis for Grouped Data-Gibbs Sampling Method

分组数据是可靠性试验中常见的一类不完全数据，由于似然函数比较复杂使Bayes分析很困难。本文利用Gibbs抽样方法，对分组数据的Bayes分析就容易实现，在寿命分布是威布尔分布情形，本文还给出了Gibbs抽样和Metropolis算法杂合的抽样方法，最后还讨论了Gibbs抽样方法的一些特点，并通过一些模拟结果对现有的几种处理分组数据的方法进行了比较。

Grouped data is a very common type of incomplete data in life tests, usually it is diflicult to make Bayes annalysis because of the complication of likelihood function. In this paper,by using Gibbs Sampling method, we can see Bayes annalysis for grouped data is readily,and in the case of Weibull distribution,the hybrid of Gibbs sampling method and Metropolis algorithm is presented , some performances of Gibbs sampling method are discussed, in the end, by some simulated results,the Bayes annalysis is compared with several existed method for dealing with grouped data.