Resumen de Effect of Not Having Homogeneous Test Units in Accelerated Life Tests
Ramón V. León, Yanzhen Li, Frank M. Guess, Rapinder S. Sawhney
The information obtained at high stress levels in accelerated life tests is generally extrapolated with an appropriate statistical model to estimate parameters of interest at normal stress levels. However, these statistical analyses do not take batch differences into consideration when they are present, and a regression model with random effects is required. It is shown in this study that ignoring batch differences in modeling can result in overly precise estimates of probabilities of failure at normal stress level.
