Consider k (k ≥ 2) independent exponential populations possibly with different location parameters (also referred to as guaranteed life spans) and a common known scale parameter. The goal is to select a non-empty subset of k exponential populations which includes the "best" population, i.e. the one associated with largest value of the location parameter. Critical constants which are needed to carry out the procedure are worked out. The performance of proposed procedure in comparison to the existing procedure is assessed through Monte Carlo method, with interesting results. The proposed method is also illustrated with the help of a real life data set.
展开▼