Inference for an exponentiated half logistic distribution with application to cancer hybrid censored data

Abstract

In this paper, based on hybrid censored sample from a two parameter exponentiated half logistic distribution, we consider the problem of estimating the unknown parameters using frequentist and Bayesian approaches. Expectation-Maximization, Lindley’s approximation and Metropolis-Hastings algorithms are used for obtaining point estimators and corresponding confidence intervals for the shape and scale parameters involved in the underlying model. Data analyses involving the survival times of patients suffering from cancer diseases and treated radiotherapy and/or chemotherapy have been performed. Finally, numerical simulation study was conducted to assess the performances of the so developed methods and conclusions on our findings are reported.

Keywords:

• Bayesian estimation
• Credible intervals
• Hybrid Type I censoring
• Lindley’s method
• Maximum likelihood estimation
• Metropolis-Hastings algorithm

Mathematics Subject Classification (2010):

• 62F10
• 62F15
• 62F25
• 62G30

Acknowledgments

The research work of the first and fourth authors was funded by the Deanship of Scientific Research (DSR), King Abdulaziz University, Jeddah, under grant no. (22-135-35-HiCi). The authors, therefore, acknowledge with thanks DSR technical and financial support. The authors would like to express their gratitude and thanks to the referees for their helpful comments and suggestions.