Performance Evaluations of Comparison-with-a-Standard Procedures

We investigate the performance of a heuristic sequential procedure to compare a finite number of designs with respect to a single standard. The goal is to identify the best design, and if the chosen best design is not the standard, to determine whether the chosen best design is better than the standard. We give preferential status to the standard because there are costs and time involved in replacing the standard. We accomplish this goal by extending indifference-zone selection procedures. An experimental performance evaluation demonstrates the validity and efficiency of our sequential procedures