The most frequent questions for reliability are 1) how many units do I need to test if I want to estimate the Weibull 0.10 quantile (B10) and 2) how long to I need to run the test? The sample size needed to estimate B10 depends on the precision required, the amount of variability in the failure times and the expected number of failures. Both analytical and simulation methods are available for assessing the precision needed for testing reliability. View a video on this topic by Bill Meeker and a related JMP demo by Leo Wright.
This webcast is part of the Statistical Methods for Reliability with Dr. Meeker on-demand webcast series.