In the theory and practice of statistical inference, multiple decision problems are encountered in many experimental situations. The classical methods for analyzing data do customarily employ hypothesis testing in most situations. In such cases, when the hypothesis is rejected, one wants to know on which of a number of possible ways the actual situations is fit our goal. If in the formulation of the problem, we consider only two decisions (reject or not reject the hypothesis), we will not only neglect to differentiate between certain alternative decisions but may also be using an inappropriate acceptance region for the hypothesis. Moreover, the traditional approach to hypothesis testing problems is not formulated in a way to answer the experimenter’s question, namely, how to identify the hypothesis which is satisfying the goal. Furthermore, when performing a test one may commit one of two errors: rejecting the hypothesis when it is true or accepting it when it is false. Unfortunately, when the number of observations is given, both probabilities cannot be controlled simultaneously by the classical approach). Kiefer (JASA 72:789–827, 1977) gave an example to show that for some sample values an appropriate test does not exhibit any detailed data-dependent measure of conclusiveness that coveys our stronger feeling in favor of the alternative hypothesis. To enforce Kiefer’s point, Schaafsma (Ann Math Statist 40:1684–1720, 1969). pointed out the Neyman-Pearson formulation is not always satisfactory and reasonable (Gupta and Huang, Multiple Decision Theory: Recent Developments, Lecture Notes In Statistics, vol. 6. Springer, New York, 1981).