A Bayes analysis of modified Weibull distribution via Markov chain Monte Carlo simulation

This paper presents the posterior analysis of a new family defined in the literature as modified Weibull distribution. This family is a modification of the two-parameter Weibull model in the sense that it, besides covering increasing and decreasing hazard rates, also represents bathtub-shaped behaviour. Both the Gibbs sampler and the Metropolis algorithms have been used to provide complete analysis of the concerned posterior surfaces. The paper also considers examining the issue of model validation using predictive simulation ideas and the Bayesian p-value. Finally, numerical illustration has been provided based on two real data sets.