Ro’ya Al-Dibi’i
Mathematical Department, Irbid National University, Irbid, Jordan
Anas A. Ababneh
Department of Statistics, Yarmouk University, Jordan
Wael Mahmoud Mohammad Salameh
Faculty of Information Technology, Abu Dhabi University, Abu Dhabi, United Arab Emirates
Mayada Abualhomos
Mathematics Department, faculty of Science, Applied Science Private University (ASU), Amman, Jordan
Ahmad A. Abubaker
Faculty of Computer Studies, Arab Open University, Saudi Arabia
Jenan Shtayat
Department of mathematics, Yarmouk University, Irbid 21163, Jordan
Ahmed Atallah Alsaraireh
The University of Jordan–Aqaba Department of computer information systems
This study introduces the Weibull-G Exponential (WGE) distribution as a flexible and robust model for reliability and lifetime data analysis. The maximum likelihood estimators (MLEs) of the distribution parameters are derived and their performance is assessed through simulation studies. In addition, a Bayesian estimation framework is developed under independent Gamma priors, with posterior distributions obtained via the Metropolis–Hasting’s algorithm within a Markov Chain Monte Carlo (MCMC) framework. Bayesian point estimates are calculated using both symmetric (Squared Error) and asymmetric (Linex) loss functions, and 95% credible intervals are constructed to quantify uncertainty. The proposed methodology is applied to carbon fiber tensile strength data, demonstrating that the WGE distribution effectively captures heavy-tailed and skewed behavior. Results indicate that both MLE and Bayesian estimates provide reliable and consistent parameter estimation, while Bayesian credible intervals offer additional insight into estimation uncertainty. The study highlights the practical utility of the WGE model and the advantages of Bayesian inference for real-world lifetime data analysis.
