Applying locally optimal criterion for classifying highly-reliable products with a control

At the research and development stage, decision-makers may wish to classify several competing designs with respect to a control (or standard) one. The classification problem may become very difficult when the products are highly reliable, since only a few (or even no) failures may be observed under normal use condition. The accelerated life test model resolves this difficulty by shortening the time of life testing and quickly provides life data of products. For highly-reliable products with a Weibull log-linear model, we propose a classification rule based on a locally optimal criterion. A suitable sampling plan based on this rule is also developed. The performance of this rule is compared with a pairwise comparison classification rule. It is shown that the sample sizes needed for the new rule are considerably lower than those needed for the pairwise comparison rule.