Empirical Bayesian Inference for Shape-Scale Family Based on the Generalized Progressive Hybrid Censoring Scheme

Résumé

Abstract In this study, the empirical Bayes method has been applied to a general lifetime model based on the generalized progressive hybrid censored scheme and compared to the fully Bayes method and the maximum likelihood method. The comparisons are made in terms of the root mean squared errors via Monte Carlo simulations. The simulation results are quite favorable to the fully Bayesian model based on the informative prior. However, the empirical Bayes provides better estimates and outperforms the maximum likelihood estimates and the fully Bayes based on the same prior or when there is a wrong choice of the prior hyperparameters. Finally, a numerical example is given to demonstrate the efficiency of the proposed methods.

Citer ce document

Accès au document

Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter

Voir l'article sur le site de la revue

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0