Bayesian Analysis of Progressive Type I Interval Censored Data - Using R2WinBUGS package

Abstract

In this talk, the Bayesian estimation of progressive type I interval censored data from Burr type XII distribution is firstly discussed. The R2WinBUGS package of R software provides an easy way for researchers to operate data manipulation in R and do parameter estimation by applying MCMC method in WinBUGS.??? To analyze progressive type I interval censored data, R calls WinBUGS, with the use of R2WinBUGS package, in the batch mode to execute the Gibbs sampling scheme that applies the Metropolis-Hastings algorithm by specifying the posterior likelihood, proportional to a product of the likelihood and parameter prior distributions. The results are again returned to R for further statistical procedures.??? Extensive simulation studies are conducted to investigate the accuracy of the developed methods. A real data set containing 112 patients with plasma cell myeloma is then analyzed for illustration. Finally, this approach is generalized to other distributions.Keywords：R, WinBUGS, Censoring, Monte Carlo Markov chain