Bayes estimation of dynamic cumulative residual entropy for Pareto distribution under type-II right censored data

• Published in: Applied mathematical modelling Vol. 40; no. 19-20; pp. 8424 - 8434
• Main Authors: Renjini, K.R., Abdul Sathar, E.I., Rajesh, G.
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.10.2016
• Subjects: Asymmetric loss function; Bayesian estimation; Dynamic cumulative residual entropy; Informative prior; Non-informative prior; Symmetric loss function; Bayesian estimation; Dynamic cumulative residual entropy; Informative prior; Symmetric loss function; Asymmetric loss function; Non-informative prior
• ISSN: 0307-904X
• DOI: 10.1016/j.apm.2016.04.017

•GP have smaller PR compared to NIPs for the estimation of alpha.•UP and EP have smaller PR for all loss functions except GELF for DCRE.•We suggest GP & GELF for α and JP & SELF for DCRE. Information measures play a vital role in reliability modeling and survival analysis of life time data. In this article, we propose the Bayesian estimation of the dynamic cumulative residual entropy for the classical Pareto distribution using a type-II right censored data. Pareto distribution can be used to model many data arising from reliability studies. To derive the corresponding posterior distributions, we use a class of informative and non-informative priors. We derive the Bayes estimators and their associated posterior risks under different symmetric and asymmetric loss functions. We illustrate the application of the proposed Bayesian estimation procedure using the (Dyer, 1981) annual wage data. To demonstrate the closeness of the Bayes estimators with the true value of the parameters, we have carried out a simulation study. The main interest in this paper is to identify an appropriate combination of a loss function and a prior which minimizes the Bayesian posterior risk.