Bayesian and Classical Inference Under Progressive Type-II Censored Samples of the Two-parameter Pareto Distribution with Binomial Random Removals Scheme
摘要
This article discusses the point and interval estimation problems for the parameters of Pareto distribution under progressive type II censoring with random removals, wherein the number of units removed at each failure time follows a binomial distribution. The parameters estimators are then obtained using maximum likelihood and Bayesian procedures. Bayesian estimates are derived with the Power Gamma joint distribution as an informative prior, Jeffery’s non-informative joint prior and based on squared and absolute error loss functions. Performance of the different approaches is compared and, in particular, the influence of the binomial parameter p on the estimation results is shown based on the simulation study. Furthermore, the suitability of the considered model and proposed methodology has been illustrated through a real data set.