Stochastically Ordered Subpopulations and Optimal Burn-In Procedure

Burn-in is a widely used engineering method which is adopted to eliminate defective items before they are shipped to customers or put into operation. In the studies of burn-in, the assumption of a bathtub shaped failure rate function is usually employed, and optimal burn-in procedures are investigated. In this paper, however, we assume that the population is composed of two ordered subpopulations, and optimal burn-in procedures are studied in this context. Two types of risks are defined, and an optimal burn-in procedure is studied which minimizes the weighted risks. The joint optimal solutions for the optimal burn-in procedure, which minimizes the mean number of repairs during the field operation, are also investigated.