Type-I censoring is one of the most commonly encountered censoring methods in practice since the total time of the experiment is under control of the experimenter and is fixed prior to the start of the life-testing experiment. In this talk, a goodness-of-fit test procedure is proposed for some lifetime distributions when the available data are subject to Type-I censoring. In particular the exponential, Weibull and log-normal models will be considered. The new test recovers the nominal level of significance and exhibit more power in compare to the existing tests for several alternative distributions by means of Monte Carlo simulations.
