Abstract: 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.