Estimation of the parameters of the generalized inverted Kumaraswamy distribution under the first failure-censored sampling plan
Paper ID : 1024-ISCHU
Authors
Mohammed Yusuf *
Department of Mathematics, Faculty of Science, Helwan University, Ain Helwan, Cairo, Egypt.
Abstract
In this paper we develop approximate Bayes estimators of the shape parameters of the generalized inverted Kumaraswamy (GIKum) distribution based on the progressive first-failure censored plan. Life testing experiments are usually time consuming and costly. We therefore, use various types of censoring schemes to cut short the experiment. The censoring scheme in an experiment may also arise naturally without the control of the experimenter. There are situations in real life where lifetimes of items are very high and test facilities are limited. We consider the maximum likelihood and Bayesian estimations with gamma-informative prior distribution for the parameters, reliability function, hazard rate and reversed hazard rate functions. We apply the Lindley’s approximation and Markov Chain Monte Carlo (MCMC) methods. The Bayes estimators have been obtained relative to both symmetric (squared error) and asymmetric (linex and general entropy) loss functions. Finally, to assess the performance of the proposed estimators, some numerical results using simulation study concerning different sample sizes are given.
Keywords
Generalized inverted Kumaraswamy distribution, progressive first-failure censored, loss functions, Lindley’s approximation
Status: Abstract Accepted (Oral Presentation)