Robust Bayesian analysis for exponential parameters under generalized Type-II progressive hybrid censoring

ABSTRACT

The Type-II progressive hybrid censoring scheme has received wide attention, but it has a disadvantage in that long time may be required to complete the life test. The generalized progressive Type-II hybrid censoring scheme has recently been proposed to solve this problem. Under the censoring scheme, the time on test does not exceed a predetermined time. In this paper, we propose a robust Bayesian approach based on a hierarchical structure when the generalized progressive Type-II hybrid censored sample has a two-parameter exponential distribution. For unknown parameters, marginal posterior distributions are provided in closed forms, and their statistical properties are discussed. To examine the robustness of the proposed method, Monte Carlo simulations are conducted and a real data set is analyzed. Further, the quality and adequacy of the proposed model are evaluated in an analysis based on the real data.

KEYWORDS:

• Generalized Type-II progressive hybrid censoring
• robust Bayesian estimation
• two-parameter exponential distribution.

MATHEMATICS SUBJECT CLASSIFICATION:

• 62F15
• 62N02

Acknowledgments

The authors are grateful to the editor-in-chief, an associate editor, and anonymous referees for their helpful comments.

Additional information

Funding

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. 2015R1D1A1A01057847).