BAYESIAN ESTIMATION FOR THE B-BIRNBAUM-SAUNDERS DISTRIBUTION

Abstract

In this article, we present Bayes estimators for the parameters and reliability function of
the -Birnbaum-Saunders distribution under both the symmetric (squared error, SE) loss
function and asymmetric (LINEX and general entropy, GE) loss functions. The Bayes estimators
can not be obtained in closed form. Approximate Bayes estimators are computed
using Lindley’s approximation technique. Posterior variance estimates are compared with
the variance of the maximum likelihood estimators (MLEs) of the parameters. The different
loss functions are compared through posterior risk. A real data set is analyzed for
illustrative purpose.