Optimum Plan for Step-Stress Accelerated Life Testing Model under Type-I Censored Samples

摘要

A simple step-stress accelerated life test plan is developed for two parameters Lomax distribution under type-I censoring. The scale parameter of the lifetime distribution at any constant stress level is assumed to be a log linear function of the stress level. The maximum likelihood function is derived for step-stress accelerated life testing model with type-I censoring. The Fisher information matrix and the asymptotic variance are obtained. The optimum plan is proposed by minimizing the asymptotic variance of the maximum likelihood estimators of the mean life at a specified design stress with respect to stress change time. A numerical study, is carried out to justify the proposed optimum plan based on the simulated data and the confidence interval of the model parameters that based on asymptotic normality of the maximum likelihood estimates are also obtained.