On interval estimation methods for the location parameter of the Weibull distribution: An application to alloy material fatigue failure data

Abstract

Abstract–The Weibull distribution is the most applied model in reliability field for lifetime analysis. The Weibull location parameter, characterizing the minimum possible life, plays a significant role in engineering applications. In this paper, we consider the interval estimation on the location parameter when the product’s lifetime follows the three-parameter Weibull distribution with a known shape parameter. A novel approach based on the relationship between the minimum order statistics, the location parameter, and the sample size is developed to construct confidence intervals for the Weibull location parameter. Thereafter, we compare it with other two interval estimation approaches by the performances of the coverage probability and the average length via simulations and a real application. The results show that the proposed method outperforms the pivot quantity (PQ) method and the bias-corrected and accelerated (Bca) bootstrap method in small and medium samples in terms of coverage probability.

keyword:

• Weibull distribution
• location parameter
• interval estimation
• fatigue failure lifetime
• Monte Carlo simulation

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was made by National Science and Technology Major Project (J2019-V-0009-0103) and National Natural Science Foundation of China (52005087).