Abstract

In life testing problems engineers must often deal with lifetimes data that are non-homogeneous. The two-component Weibull mixture is then a highly relevant model to capture heterogeneity for a large majority of operating lifetimes. Unfortunately, the performance of classical estimation methods is risked due to the high number of parameters. The Weibull mixture parameters estimation, in this research we propose a Bayesian Approximation by Lindley approach to provide the posterior density. In this paper we dealt with the estimation of an unknown scale parameter of the two parameter Weibull distribution with Squared Error loss function suggested in this paper.It deals with the methods to obtain the approximate Bayes estimators of the Weibull distribution by using Lindley approximation technique for type-II censored samples. A bivariate prior density for the parameters, squared error Loss function (SELF), are used to obtain the approximate Bayes Estimators. A numerical calculation is done for approximate Bayes estimator and its relative mean squared errors by R programming to present the statistical properties of the estimators.

Description