Likelihood Based Inference on Progressive type-II hybrid-censored data For Burr Type III Distribution

In this article we discuss about the problem of estimate the Burr type III distribution parameters based on progressive type II hybrid censored data. Because the estimation of these parameters is complex and has not closed form. So we use the EM and stochastic EM algorithm (SEM) for estimating the parameters of this distribution which based on the missing data. Then, a Mont Carlo simulation study is conducted to assess the accuracy of proposed estimators. The results revealed that SEM and EM have better performances than MLE estimates based on Newton-Raphson method and parameter estimates are improved when the sample size is increasing.