Correlation induction without the inverse transformation

ABSTRACT

Inducing correlation between estimators is a common way to try to reduce variance in simulation experiments. To induce the correlation between estimators, random variates are generated as functions of the same random-number streams. Although the optimal correlation induction occurs with the inverse transformation. The inverse can be quite slow compared to other methods for generating random variates. We discuss an approach for generating random variates quickly while still obtaining substantial correlation induction.

REFERENCES

• 1: Ahrens, J.H. and Kohrt, K.D. (1981). "Computer Methods for Efficient Sampling from Largely Arbitrary StuLlstlcal Distributions,~ Computing 26, 19-31.
• 2: Rrutley, P., Fox, B.L. and Schrage, L.E. (1983). A Guide to Simulation. Sprlnger-Verlag, New York.
• 3: Chert, H.C. and Asau, Y. (1974). "'On GeneraLlng Random Varlates from an Empirical Dls~rlbu~lon," AIIE Transactions 6, 183-166.
• 4: Cheng, R.C.H. (1982). "The Use or AnLlthetic Varlates in Computer Slmulatlons,'" Journal of the Operational Research Society 33, 229-237.
• 5: Devroye, Luo (1986). Non-Uniform Random Variate Generation. Sprlnger-Verlag, New York.
• 6: Flshman, G.S. and Moore, L.R. III (1984). "Sampllng from a Dlscrete Dlstrlbutlon while Preserving Monotonlclty," The American Statistician 38, 219-223.
• 7: Kachltvlchyanukul, V., Cheng, S-W.J. and Schmelser, B. (1985). "Fast Polsson and Blnomlal Algorithms for Correlatlon Induction," Technical Report 86-1, Department of Industrial and Management Engineering, The University of Iowa.
• 8: Nelson, B.L. (1986). "A Perspectlve on Varlance Reduction In Simulation Experiment, s," Working Paper Series 1985-011, Department of Industrial and Systems Engineering, The Ohio State University.
• 9: Schmelser, B.W. (1980). "Random Varlate Generation: A Survey." In: Simulation with Discrete Models: A State-of-the-Art View, Volume 2 of Proceedings of the Winter Simulation Conference, (T.I. Oren, C.M. Shub, and P.F. Roth, eds.). IEEE, New York, 7Q-I04.
• 10: Schmelser, B.W. and Babu, A.J.G. (1980). "Beta Varlate Generation Via Exponential Majorlzlng Functions,'" Operations Research 28, 917-926.
• 11: Wilson, J.R. (1984). "'Variance Reduction Techniques for Digital Simulation," American Journal of Mathematical and Management Sci~nc~~ 4, 277-312.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.6 SIMULATION AND MODELING

Additional Classification:
  G. Mathematics of Computing

  I. Computing Methodologies
  I.6 SIMULATION AND MODELING

General Terms:
Algorithms, Design, Experimentation, Performance, Theory