Optimum 3-stage, step-stress accelerated life tests plan under progressively type I censored data with random removals

Optimum simple (2-stage) step stress accelerated life testing plans have practical lim-itation. They highly depend upon the assumption of a linear relationship between stress and time to failure and use only two extreme strsses that can cause irrelevant failure modes. Thus, 3-step plans are preferable. This article introduces a 3-stage step-stress accelerated life test. This paper considers the analysis of generalized inverted exponential distributed lifetime data observed under progressive type I censoring with random removal, where the number of units removed at each stress follows a binomial distribution. The problem of choosing the optimal times τ1 and τ2 under 3-stage step stress is addressed by minimizing the asymptotic variance of the maximum likelihood estimator of reliability at time ξ. Finally, the simulation results are discussed to illustrate the effect of the initial estimates on the optimal values