In this paper, we talk mainly about statistical analysis of censored samples. Censored samples may arise in practice in different way. For example, in life testing experiments. We talk about it in three parts.1. Present the maximum likelihood estimation for the parameter of a general class of distributions with grouped and censored data by EM algorithm. The class of distributions includes the Weibull, Reyleigh, Burr- type X II, Pareto and Beta distribution.2. Observables, a general class of distributions, are to be predicted using the Bayesian approach. Predictive density functions are abtained in one- and two-sample cases when the history sample is a multiply type II censored samples. Illustrative example are given.3. With multiply type II censored samples, we also obtain the Bayes estimations of the Burr-type X II distribution parameters, and give a sample approximation.
|