Abstract

This work investigates a simple step-stress accelerated life testing plan based on progressive Type-II censoring for units whose lifetimes follow the TDUSW distribution. The cumulative exposure model is adopted to describe the effect of changing stress levels during the experiment. Under this framework, the probability density function and the cumulative distribution function of the TDUSW distribution are incorporated into the likelihood structure of the progressively censored sample. Maximum likelihood estimators of the distribution parameters are derived, and numerical procedures are suggested to obtain their estimates. In addition, the asymptotic variance–covariance matrix is computed via the observed Fisher information. A real data example and a simulation study are presented to illustrate the performance of the estimators under various censoring schemes. The results demonstrate that the TDUSW model provides a flexible structure for modeling accelerated life-testing data and yields stable parameter estimates even under moderate censoring.