Testing for initialization bias in simulation output

Abstract

A test is presented for detecting the presence of initialization bias in the mean of a simulation output process. The test is based on a standardized sequence of linear combinations of the ranks of the simulation observations. The validity and power of the test are illustrated by applying it to a large number of in dependently seeded experiments on the M/M/s queue with s=1 and s= 4.

Keywords

initialization bias simulation output testing

Get full access to this article

View all access options for this article.

References

Billingsley P. 1968. Convergence of Probability Measures. Wiley, London.

Cafarian A.V. , C.J. Anker , Jr. and T. Morisaku 1978. "Evaluation of Commonly Used Rules for Detecting 'Steady State' in Computer Simulation". Naval Res. Logist. Quart. 25: 511-529.

Fishman G.S. 1978. Principles of Discrete Event Simulation. Wiley, New York.

Gibbons J.D. 1971. Nonparametric Statistical Inference. McGraw-Hill, London.

Hoyland A. 1968. "Robustness of the Wilcoxon Estimate of Location Against a Certain Dependence". The Annals of Math. Statistics 39, no. 4: 1196-1201.

Huber P.J. 1981. Robust Statistics. Wiley, New York.

Kleinrock L. 1975. Queueing Systems, Vol. 1: Theory. Wiley, New York.

Law A.M. 1983. "Statistical Analysis of Simulation Output Data". Operations Research 31, no. 3: 983-1029.

Schruben L.W. 1982. "Detecting Initialization Bias in Simulation Output". Operations Research 31, no. 3: 569-590.

10.

Schruben L.W. , H. Singh and L. Tierney 1983. "Optimal Tests for Initialization Bias in Simulation Output". Operations Research 31, no. 6: 1176-1178.

11.

Wilson J.R. and A.B. Pritsker 1978. 'A survey of Research on the Simulation Startup Problem". Simulation 31, no. 4: 55-58.