Analyzing stress-strength reliability δ=P[U<V<W]: a Bayesian and frequentist perspective with Burr-XII distribution under progressive Type-II censoring

This research focuses on estimating the stress-strength reliability in a system characterized by the influence of two random stresses on its strength, employing both frequentist and Bayesian approaches. The reliability of such systems is represented by the function δ = P ( U < V < W ) , where...

Full description

Saved in:
Bibliographic Details
Published in:International journal of system assurance engineering and management 2024, Vol.15 (6), p.2453-2472
Main Authors: Nayal, Amit Singh, Singh, Bhupendra, Tripathi, Vrijesh, Tyagi, Abhishek
Format: Article
Language:English
Subjects:
Asymptotic methods
Bayesian analysis
Confidence intervals
Engineering
Engineering Economics
Logistics
Marketing
Markov chains
Maximum likelihood estimators
Monte Carlo simulation
Organization
Original Article
Quality Control
Random variables
Reliability
Reliability analysis
Safety and Risk
Statistical analysis
Stresses
System reliability
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This research focuses on estimating the stress-strength reliability in a system characterized by the influence of two random stresses on its strength, employing both frequentist and Bayesian approaches. The reliability of such systems is represented by the function δ = P ( U < V < W ) , where V denotes the system’s strength, and U and W represent the stresses. The analysis is performed under a progressive Type-II censoring scheme, considering the random variables U , V , and W as independent and following the Burr-XII distribution. In a frequentist setup, both the maximum likelihood estimator and the maximum product spacings estimator of δ have been obtained. In the Bayesian paradigm, the Bayes estimator of δ under the squared error loss function is derived utilizing the Markov chain Monte Carlo method, considering independent gamma priors for the unknown parameters. In addition, asymptotic confidence intervals and highest probability density credible intervals for δ are also formulated. An extensive simulation experiment is carried out to compare the performances of the different developed estimators. Finally, a real-life application is presented to demonstrate the practical applicability of the proposed theory.
ISSN:0975-6809
0976-4348
DOI:10.1007/s13198-024-02264-4