Affiliations:
1Department of Statistics, Faculty of Sciences, King Abdulaziz University, Jeddah 21589, Saudi Arabia
2Department of Statistics, Faculty of Commerce (Girls’ Branch), Al-Azhar University, Cairo, Egypt
3Basic Sciences Department, Higher Institute of Marketing, Commerce and Information Systems (MCI), Cairo, Egypt
This paper introduces an adaptive Type II progressive censoring strategy to improve Bayesian analysis of survival data in life-testing experiments. Using adaptively censored data, the Chen–Burr XII distribution is examined, and Bayesian estimators are derived for its parameters, reliability, hazard rate, and reversed hazard rate under squared error and linear exponential loss functions, assuming independent gamma priors. Credible intervals are constructed to measure parameter uncertainty, and the adaptive Metropolis algorithm is used for Bayesian computation. A simulation study based on four censoring schemes evaluates estimator performance in terms of bias and posterior risk. The results show that estimation efficiency increases with larger sample sizes, more observed failures, and smaller prior variance. Furthermore, the linear exponential loss function with a smaller shape parameter provides more efficient estimates than both larger shape parameters and the squared error loss function. The study also discusses broader methods for developing lifetime distributions, such as transformations and mixtures, and highlights the value of the competing risks approach for modeling events with multiple causes across various fields. The practical usefulness of the proposed methodology is demonstrated through the analysis of real censored lifetime data, including COVID-19 survival data.
Adaptive progressive censoring, Bayesian estimation, Chen–Burr XII distribution, Survival analysis, Competing risks
https://doi.org/10.21833/ijaas.2025.12.015
Kalantan, Z. I., & Salem, H. N. (2025). Adaptive Bayesian survival modeling with the Chen–Burr XII distribution: Theory and application to censored COVID-19 data. International Journal of Advanced and Applied Sciences, 12(12), 158–183. https://doi.org/10.21833/ijaas.2025.12.015