Bayesian and likelihood estimation of multicomponent stress–strength reliability from power Lindley distribution based on progressively censored samples

Abstract

In this article, the problem of estimation of reliability of a ℓ-component system when both the stress and strength components are assumed to have a power Lindley distribution is discussed. The multicomponent stress–strength reliability parameter is obtained using both the Bayesian and the classical approaches when component-wise each unit follows a power Lindley distribution. To estimate the multicomponent stress–strength reliability parameter under the classical approach, the method of maximum likelihood and the asymptotic confidence interval estimation method are used as point and interval estimation methods, respectively. Under the Bayesian paradigm, the reliability parameter is estimated under the linear exponential loss function using the Lindley approximation, the Tierney–Kadane approximation and the Markov chain Monte Carlo (MCMC) techniques and subsequently highest posterior density credible intervals are obtained. To validate the efficacy of the proposed estimation strategies, a simulation study is carried out. Finally, two real-life data sets are re-analysed for illustrative purposes.

KEYWORDS:

• Power Lindley distribution
• progressive censoring
• multicomponent stress–strength reliability
• maximum likelihood estimation
• Bayesian estimation

Acknowledgements

The authors are grateful to the Editor-in-Chief, Associate Editor and the learned reviewers for their insightful and constructive comments that led to possible improvements in the earlier version of this article.

Disclosure statement

No potential conflict of interest was reported by the author(s).