Bayesian Estimation of Parameter of Gamma Distribution with Multiple Change Points for Randomly Truncated and Censored Data
HE Chao-bin · Journal of Sichuan Normal University · 2015
In this paper,the complete-data likelihood function of gamma distribution for randomly truncated and censored data was obtained after adding data. The full conditional distributions of change-point positions and other parameters were investigated to get Gibbs samples of the parameters by MCMC method of Gibbs sampling together with Metropolis-Hastings algorithm. Taking the means of Gibbs samples as the Bayesian estimations of the parameters,random simulation test results show that the Bayesian estimations of the parameters are fairly accurate.