Optimal progressive interval censoring plan under accelerated life test with limited budget

ABSTRACT

In this paper, we investigate some inference and design problems related to multiple constant-stress accelerated life test with progressive type-I interval censoring. A Weibull lifetime distribution at each stress-level combination is considered. The scale parameter of Weibull distribution is assumed to be a log-linear function of stresses. We obtain the estimates of the unknown parameters through the method of maximum likelihood, and also derive the Fisher's information matrix. The optimal number of test units, number of inspections, and length of the inspection interval are determined under D-optimality, T-optimality, and E-optimality criteria with cost constraint. An algorithm based on nonlinear mixed-integer programming is proposed to the optimal solution. The sensitivity of the optimal solution to changes in the values of the different parameters is studied.

KEYWORDS:

• D-optimality
• E-optimality
• maximum likelihood method
• multiple constant stress
• T-optimality
• Weibull distribution

Acknowledgments

The authors wish to thank the Associate Editor and referee for valuable suggestions which led to the improvement of this paper.

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Shuo-Jye Wu  http://orcid.org/0000-0001-7294-8018

Additional information

Funding

The work of the first author was partially supported by the Ministry of Science and Technology of ROC grant MOST 104-2118-M-032-007.