Bayesian analysis of randomly censored Burr type XII distribution under different loss functions


The paper deals with Bayesian estimation of unknown parameters of Burr type XII distribution under the Koziol-Green model of random censorship assuming both the informative and noninformative priors. We use different symmetric and asymmetric loss functions to obtain the Bayes estimates. It is seen that the closed-form expressions for the Bayes estimators cannot be obtained; we propose Gibbs sampling scheme to obtain the approximate Bayes estimates.  Monte Carlo simulation is carried out to observe the behavior of the proposed estimators and also to compare with the maximum likelihood estimators. Based on the simulation study, we propose a set of estimators of the model parameters. One real data analysis is performed and it is seen that the proposed set of estimators fit the data best than the rest.

DOI Code: 10.1285/i20705948v7n2p326

Keywords: Random censoring; Bayes estimate; log-concave density; Gibbs sampling; Markov chain Monte Carlo.

Full Text: pdf

Creative Commons License
This work is licensed under a Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia License.