On three-parameter exponential distribution: properties, Bayesian and non-Bayesian estimation based on complete and censored samples. Issue 11 (2nd November 2021)

• Record Type: Journal Article
• Authors: Afify, Ahmed Z.; Suzuki, Adriano K.; Zhang, Chunfang; Nassar, Mazen
• Is Part Of: Communications in statistics. Volume 50:Issue 11(2021)
• Page Start: 3799
• Page End: 3819
• Publication Date: 2021-11-02
• Subjects: Bayesian estimation -- Exponential distribution -- Maximum likelihood -- Moment -- Type-II censored data; Mathematical statistics -- Periodicals; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5
• DOI: 10.1080/03610918.2019.1636995
• Languages: English
• ISSNs: 0361-0918

Abstract

Abstract: In this paper we introduce a new three parameter distribution called the generalized odd log-logistic exponential (GOLLEx) distribution. The proposed distribution possesses a very flexible hazard rate function shapes which provide a more flexibility in data analysis. We study the main properties of the proposed distribution including quantiles, moments, moment generating function. We obtain the maximum likelihood and Bayes estimates of the GOLLEx distribution based on complete and type-II censored data. The Bayes estimates of the unknown parameters are obtained by using the Markov Chain Mont Carlo (MCMC) approach under the assumption of the independent gamma priors. We perform a simulation study to compare the performance of the different estimators. Finally, we analyze a real data set under the complete sample case to show the applicability of the proposed estimates.