Paper Info
Title
Robust Bayesian estimation of a bathtub-shaped distribution under progressive Type-II censoring
Abstract
The bathtub-shaped failure rate function has been used for modeling the life spans of a number of electronic and mechanical products, as well as for modeling the life spans of humans, especially when some of the data are censored. This article addresses robust methods for the estimation of unknown parameters in a two-parameter distribution with a bathtub-shaped failure rate function based on progressive Type-II censored samples. Here, a class of flexible priors is considered by using the hierarchical structure of a conjugate prior distribution, and corresponding posterior distributions are obtained in a closed-form. Then, based on the square error loss function, Bayes estimators of unknown parameters are derived, which depend on hyperparameters as parameters of the conjugate prior. In order to eliminate the hyperparameters, hierarchical Bayesian estimation methods are proposed, and these proposed estimators are compared to one another based on the mean squared error, through Monte Carlo simulations for various progressively Type-II censoring schemes. Finally, a real dataset is presented for the purpose of illustration.
Year
DOI
Venue
2017
10.1080/03610918.2014.988256
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
Keywords
Field
DocType
Bathtub-shaped distribution,Hierarchical Bayes estimation,Hyperparameter,Progressively Type-II censoring
Econometrics,Hyperparameter,Mean squared error,Bayesian hierarchical modeling,Prior probability,Statistics,Censoring (statistics),Bayes estimator,Conjugate prior,Mathematics,Estimator
Journal
Volume
Issue
ISSN
46
2
0361-0918
Citations 
PageRank 
References 
0
0.34
3
Authors
3
Name
Order
Citations
PageRank
jung in seo100.34
suk bok kang200.34
Yongku Kim316.03