USING COMMON RANDOM NUMBERS FOR INDIFFERENCE-ZONE SELECTION AND MULTIPLE COMPARISONS IN SIMULATION

We present a general recipe for constructing experiment design and ana lysis procedures that simultaneously provide indifference-zone selecti on and multiple-comparison inference for choosing the best among k sim ulated systems. We then exhibit two such procedures that exploit the v ariance-reduction technique of common random numbers to reduce the sam ple size required to attain a fixed precision. One procedure is based on the Bonferroni inequality and is guaranteed to be statistically con servative. The other procedure is exact under a specific dependence st ructure, but may be slightly liberal otherwise. Both are easy to apply , requiring only simple calculations and tabled constants. We illustra te the procedures with a numerical example.