Selecting the best by comparing simulated systems in a group of three

We present a new fully sequential procedure for selecting the best among a finite number of simulated systems. While many fully sequential selection procedures make a decision based on pairwise comparison, the new procedure compares systems in a group of three and uses some properties of a bivariate Brownian motion process exiting a circle or an ellipse for its derivation.

[1]  R. Bechhofer.  A Single-Sample Multiple Decision Procedure for Ranking Means of Normal Populations with known Variances , 1954 .

[2]  Amir Dembo,et al.  Large Deviations Techniques and Applications , 1998 .

[3]  Barry L. Nelson,et al.  A fully sequential procedure for indifference-zone selection in simulation , 2001, TOMC.

[4]  Seong-Hee Kim,et al.  Reducing the Conservativeness of Fully Sequential Indifference-Zone Procedures , 2013, IEEE Transactions on Automatic Control.

[5]  Barry L. Nelson,et al.  On the Asymptotic Validity of Fully Sequential Selection Procedures for Steady-State Simulation , 2006, Oper. Res..

[6]  David Goldsman,et al.  PERFORMANCE OF VARIANCE UPDATING PROCEDURES ON VARIOUS DATA , 2005 .

[7]  L NelsonBarry,et al.  A fully sequential procedure for indifference-zone selection in simulation , 2001 .

[8]  Barry L. Nelson,et al.  Chapter 17 Selecting the Best System , 2006, Simulation.

[9]  Stephen E. Chick,et al.  Chapter 9 Subjective Probability and Bayesian Methodology , 2006, Simulation.

[10]  Seong-Hee Kim,et al.  Performance of variance updating ranking and selection procedures , 2005, Proceedings of the Winter Simulation Conference, 2005..

[11]  E. Paulson.  A Sequential Procedure for Selecting the Population with the Largest Mean from $k$ Normal Populations , 1964 .

[12]  Y. Rinott.  On two-stage selection procedures and related probability-inequalities , 1978 .

[13]  Samuel Karlin,et al.  A First Course on Stochastic Processes , 1968 .