ESTIMATION IN CONSTANT-STRESS PARTIALLY ACCELERATED LIFE TESTS FOR BURR TYPE XII USING TAMPERED RANDOM VARIABLE MODEL UNDER UNIFIED HYBRID CENSORING DATA

Abstract

This paper discusses constant stress partially accelerated life tests for unified hybrid censoring data from Burr type XII distribution with a tampered random variable. Both maximum likelihood and Bayesian methods are used to estimate the unknown population parameters and accelerated factor. In order to compute the asymptotic confidence intervals for the maximum likelihood estimators, we first calculate the Fisher information matrix related to the underlying model. On the other hand, Markov Chain Monte Carlo method under squared error loss function is used for obtaining the corresponding Bayesian estimators. In addition, a simulation study is carried out to compare the performances of the resulting estimators.