Estimation and Prediction for Type-II Hybrid Censored Data Follow Flexible Weibull Distribution

Abstract

In this paper, we proposed Bayes estimators for estimating the parameters, reliability, hazard rate, mean time to failure from flexible Weibull distribution using Type-II hybrid censored sample. Bayes estimators have been obtained under squared error loss function assuming independent gamma prior distributions for the parameters. The maximum likelihood estimators along with asymptotic distributions have also been discussed. The performances of the estimators have been compared with respect to the various Type-II hybrid censoring schemes. For approximating the posteriors, we proposed the use of Markov chain Monte Carlo techniques such as Gibbs sampler and Metropolis-Hastings algorithm. Further, Bayesian One- andTwo-sample prediction problems have also been considered. A real data set has been analysed for illustration purposes.