Optimality in Type-II Progressive Censoring: Bayesian Approach Under the General Entropy Loss Function

Here, we consider the progressive Type-II censoring, and the sample size is determined by considering two criteria in a Bayesian prediction problem. The first criterion is the Bayes risk function of the point predictor for a future progressively censored order statistic. The second criterion is the cost of experiment designing. In the Bayesian prediction, the general entropy loss function is considered. We find the optimal sample size such that the Bayes risk function and the cost of the experiment are bounded. To show the usefulness of the results, some numerical computations are presented.