Simulation Modeling and Analysis
Simulation Modeling and Analysis
New Two-Stage and Sequential Procedures for Selecting the Best Simulated System
Operations Research
Ranking and Selection for Steady-State Simulation: Procedures and Perspectives
INFORMS Journal on Computing
Using Ranking and Selection to "Clean Up" after Simulation Optimization
Operations Research
Selecting a Selection Procedure
Management Science
Integrating techniques from statistical ranking into evolutionary algorithms
EuroGP'06 Proceedings of the 2006 international conference on Applications of Evolutionary Computing
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
The knowledge-gradient stopping rule for ranking and selection
Proceedings of the 40th Conference on Winter Simulation
Simulation optimization using the cross-entropy method with optimal computing budget allocation
ACM Transactions on Modeling and Computer Simulation (TOMACS)
Sequential Sampling to Myopically Maximize the Expected Value of Information
INFORMS Journal on Computing
Paradoxes in Learning and the Marginal Value of Information
Decision Analysis
Guessing preferences: a new approach to multi-attribute ranking and selection
Proceedings of the Winter Simulation Conference
Hi-index | 0.00 |
Statistical selection procedures can identify the best of a finite set of alternatives, where "best" is defined in terms of the unknown expected value of each alternative's simulation output. One effective Bayesian approach allocates samples sequentially to maximize an approximation to the expected value of information (EVI) from those samples. That existing approach uses both asymptotic and probabilistic approximations. This paper presents new EVI sampling allocations that avoid most of those approximations, but that entail sequential myopic sampling from a single alternative per stage of sampling. We compare the new and old approaches empirically. In some scenarios (a small, fixed total number of samples, few systems to be compared), the new greedy myopic procedures are better than the original asymptotic variants. In other scenarios (with adaptive stopping rules, medium or large number of systems, high required probability of correct selection), the original asymptotic allocations perform better.