Optimum simple step-stress plans using reliability estimate

This paper presents optimum simple step-stress plans under the log-logistic cumulative exposure model. The likelihood function of the model parameters is derived, from which the Fisher information matrix and the asymptotic variance of the reliability estimate are obtained. Optimum times of changing stress level are obtained by minimizing the asymptotic variance of the reliability estimate at a specified time under normal operating condition. Confidence intervals and hypotheses tests about the model parameters have also been discussed and illustrated by an example. Copyright Sapienza Università di Roma 2012