Abstract:
|
In many biological and industrial studies, tolerance limits are useful statistical tools for monitoring the population of interest. When the population can be split into several subpopulations via a latent variable, constructing tolerance limits can be a challenging task. In this talk, I will introduce a systematic method to obtain tolerance limits for normal mixtures. Some simulation results will be presented to demonstrate that the proposed method can maintain the empirical coverage rates sufficiently close to the nominal level. In addition, a real-life data analysis will be presented to illustrate the proposed method.
|