Best-subset selection procedure

We propose an indifference-zone approach for a ranking and selection (R&S) problem with the goal of finding the best-subset from a finite number of competing simulated systems given a level of correct-selection probability. Here the “best” system refers to the system with the largest or smallest performance measures. We present a best-subset selection procedure that can effectively eliminate the non-competitive systems and return only those alternatives as the selection result where statistically confident conclusions hold. Numerical experiments document that our procedure works well by selecting the correct best-subset with very high probability.