论文信息 - Methods for selecting the best system (for simulation)

Methods for selecting the best system (for simulation)

The authors consider three methods for selecting the best of a set of competing simulation systems: interactive analysis, ranking and selection, and multiple comparisons. They describe each method, discuss assumptions, implementation aspects, advantages, and disadvantages, and demonstrate the use of each method with an airline reservation system simulation example.<<ETX>>

[1] M. C. Bonney,et al. Simulation and Analysis of Industrial Systems , 1971 .

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

[3] Bruce W. Schmeiser,et al. Batch Size Effects in the Analysis of Simulation Output , 1982, Oper. Res..

[4] R. Wilcox. A Table for Rinott's Selection Procedure , 1984 .

[5] J. Hsu. Sample size computation for designing multiple comparison experiments , 1988 .

[6] Barry L. Nelson,et al. Batch-size effects on simulation optimization using multiple comparisons with the best , 1990, 1990 Winter Simulation Conference Proceedings.

[7] Bruce W. Schmeiser,et al. Chapter 7 Simulation experiments , 1990 .

[8] M. Hartmann,et al. A comparison of the performances of procedures for selecting the normal population having the largest mean when the populations have a common unknown variance , 1990 .

[9] Bruce W. Schmeiser,et al. Overlapping batch statistics , 1990, 1990 Winter Simulation Conference Proceedings.

[10] Wei-Ning Yang,et al. Using Common Random Numbers and Control Variates in Multiple-Comparison Procedures , 1991, Oper. Res..

[11] Bruce W. Schmeiser,et al. SERVO: Simulation experiments with random-vector output , 1991, 1991 Winter Simulation Conference Proceedings..