Inferences for the Birnbaum-Saunders fatigue life model using Bayesian methods

Abstract Expressions for the marginal posterior and predictive densities of interest considering the Birnbaum—Saunders model and using Laplace's method for integrals, when we cannot find explicitly solutions assuming different noninformative priors. In one numerical example, we consider a data set introduced by Birnbaum and Sauders ( J. Appl. Probab. 6 , 1969, p. 328–347) in order to compare the Bayesian methodology with the usual standard classical approach based on the asymptotical normal distribution for the maximum likelihood estimators of the parameters of the model.