Planning accelerated life tests under progressive type I interval censoring with random removals

This article investigates optimal accelerated life test (ALT) plans for exponentially distributed lifetimes under progressive Type I interval censoring with random removals. For different combinations of total number of inspections and removal probability, the optimal ALT plans which minimize the asymptotic variance of the estimated mean are presented. The length of the corresponding experiment is also presented. Sensitivity analysis on the asymptotic variance of the estimated mean is conducted to assess the robustness of the results with respect to the given parameters. Finally, suggestions are given to experimenters in designing an ALT under progressive Type I interval censoring with random removals.