A Fully Sequential Procedure for Indi erence-Zone Selection in Simulation

We present procedures for selecting the best or near-best of a nite number of simulated systems when best is deened by maximum or minimum expected performance. The procedures are appropriate when it is possible to repeatedly obtain small, incre-mental samples from each simulated system. The goal of such a sequential procedure is to eliminate, at an early stage of experimentation, those simulated systems that are clearly inferior, and thereby reduce the overall computational eeort required to nd the best. The procedures we present accommodate unequal variances across systems and the use of common random numbers. However, they are based on the assumption of normally distributed data, so we analyze the impact of batching (to achieve approximate normality or independence) on the performance of the procedures. Comparisons with existing procedures are also provided.