Some guidelines and guarantees for common random numbers
Management Science
A Bonferroni selection procedure when using commom random numbers with unknown variances
WSC '86 Proceedings of the 18th conference on Winter simulation
A fully sequential procedure for indifference-zone selection in simulation
ACM Transactions on Modeling and Computer Simulation (TOMACS)
Simulation Budget Allocation for Further Enhancing theEfficiency of Ordinal Optimization
Discrete Event Dynamic Systems
Using Ordinal Optimization Approach to Improve Efficiency of Selection Procedures
Discrete Event Dynamic Systems
Comparison with a Standard via All-Pairwise Comparisons
Discrete Event Dynamic Systems
Simulation Modeling and Analysis (McGraw-Hill Series in Industrial Engineering and Management)
Simulation Modeling and Analysis (McGraw-Hill Series in Industrial Engineering and Management)
Simulation Allocation for Determining the Best Design in the Presence of Correlated Sampling
INFORMS Journal on Computing
| Hi-index | 0.00 |
Indifference-zone selection procedures have been widely studied and applied to determine the sample sizes for selecting a good system or a subset of good systems among k alternative systems. It is known that using common random numbers can increase efficiency of simulation procedures, but using common random numbers may also "backfire." We show that it is generally safe to use common random numbers to increase the probability of correct selection with Dudewicz and Dalal's procedure as well as its extension for subset selection when common random numbers are properly synchronized, even though these selection procedures are derived based on independent sampling. The result is derived with correlated order statistics in a concise manner, namely, the expected value of the first-order statistic becomes larger as the (positive) covariances become stronger. We perform simulation experiments to confirm this finding.