Selecting the Best of Two Normal Populations Using a Loss Function. (RevisedVersion of 93-15)

摘要

In selection problems, the usual loss function is the 0-2 one, i.e. the selectingoal is to bound, from below, probabilities of making correct selections. In the present paper, a selection goal based on a general loss function is presented. The populations have unknown location parameters and good populations are the ones with large values of this parameter. The case of two populations is considered in detail. For this case, the selection rule is given and its performance is investigated for normal populations.