Combining two classical approaches for statistical selection

This paper presents a selection procedure that combines Bechhofer's indifference zone selec tion and Guptas subset selection approaches?? by using a preference threshold. A subset of populations is selected that have sample sums within the distance of this threshold from the largest sample sum. Aiming at designing the experiment we derive the minimal necessary sample size and the value for the preference threshold in order to satisfy two requirements for correct selection. One requirement is related to the indifference zone method the other to the subset selection method. Considered are normal populations with common known variance and several properties of the procedure are presented. The method is further discussed using simulation studies.