An extended weighted exponential distribution and its associated regression model

Abstract

In this paper, we propose a new distribution for survival data. The distribution is a new generalization of the weighted exponential distribution in the Marshall-Olkin family. Statistical properties of the proposed distribution are studied and its submodels are presented. The unknown parameters are estimated via a Bayesian approach. Simulation studies are conducted to assess the performance of the Bayesian estimator. Complete and censored data sets are analyzed to illustrate the potential of the proposed distribution. We also develop a regression model based on the proposed distribution. Finally, we compare the proposed model with other models.

Keywords

• bayesian approach
• censored data
• marshall-olkin family
• weighted exponential distribution
• regression model