Input modeling when simple models fail

ABSTRACT

A simulation model is composed of inputs and logic; the inputs represent the uncertainty or randomness in the system, while the logic determines how the system reacts to the uncertain elements. Simple input models, consisting of independent and identically distributed sequences of random variates from standard probability distributions, are included in every commercial simulation language. Software to fit these distributions to data is also available. In this tutorial we describe input models that are useful when simple models are not.

REFERENCES

• 1: Avramidis, A. N. and J. R. Wilson. 1994. A flexible method for estimating inverse distribution functions in simulation experiments. ORSA Journal on Computing 6:342-355.
• 2: Cario, M. C. and B. L. Nelson. 1995. Autoregressive to anything: Time series input processes for simulation. Working Paper, Department of industrial, Welding and Systems Engineering, The Ohio State University, Columbus, Ohio.
• 3: Devroye, L. 1986. Non-Uniform Random Variate Generation. New York: Springer-Verlag.
• 4: Stephen C. Hora, Estimation of the inverse function for random variate generation, Communications of the ACM, v.26 n.8, p.590-594, Aug. 1983 [doi>10.1145/358161.358170]
• 5: Jagerman, D. L. and B. Melamed. 1992a. The transition and autocorrelation structure of TES processes, Part I: General theory. Communication in Statistics-Stochastic Models 8:193-219.
• 6: Jagerman, D. L. and B. Melamed. 1992b. The transition and autocorrelation structure of TES processes, Part II: Special cases. Communication in Statistics-Stochastic Models 8:499-527.
• 7: Johnson, M. A., S. Lee and J. R. Wilson. 1994a. Experimental evaluation of a procedure for estimating nonhomogeneous Poisson processes having cyclic behavior. ORSA Journal on Computing 6:356-368.
• 8: Johnson, M. A., S. Lee and J. R. Wilson. 1994b. NPPMLE and NPPSIM: Software for estimating and simulating nonhomogeneous Poisson processes having cyclic behavior. Operations Research Letters 15:273-282.
• 9: Mark E Johnson, Multivariate statistical simulation, John Wiley & Sons, Inc., New York, NY, 1987
• 10: Johnson, N. L. 1949. Systems of frequency curves generated by methods of translation. Biometrika 36:297-304.
• 11: Lee, S., J. R. Wilson and M. M. Crawford. 1991. Modeling and simulation of a nonhomogeneous Poisson process haviag cyclic behavior. Communications in Statistics--Simulation and Computation 20:777-809.
• 12: Benjamin Melamed , Jon R. Hill , David Goldsman, The TES methodology: modeling empirical stationary time series, Proceedings of the 24th conference on Winter simulation, p.135-144, December 13-16, 1992, Arlington, Virginia, United States [doi>10.1145/167293.167319]
• 13: Schmeiser, B. W. and S. J. Deutsch. 1977. A versatile four parameter family of probability distributions suitable for simulation. IIE Transactions 9:176- 181.
• 14: Song, W. T., L-C. Hsiao and Y-J. Chen. 1995. Generation of autocorre}ated random variables in the analysis of simulation input. European Journal o/ Operational Research, forthcoming.
• 15: Swain, J. J., S. Venkatraman and J. R. Wilson. 1988. Least-squares estimation of distribution functions in Johnson's translation system. Journal of Statistical Computation and Simulation 29:271-297.
• 16: Mary Ann Flanigan Wagner , James R. Wilson, Using univariate Be´zier distributions to model simulation input processes, Proceedings of the 25th conference on Winter simulation, p.365-373, December 12-15, 1993, Los Angeles, California, United States [doi>10.1145/256563.256667]
• 17: Wagner, M. A. F. and J. R. Wilson. 1994a. Using univariate B~zier distributions to model simulation input processes. IIE Transactions, forthcoming.
• 18: Mary Ann Flanigan Wagner , James R. Wilson, Using bivariate Be´zier distributions to model simulation input processes, Proceedings of the 26th conference on Winter simulation, p.324-331, December 11-14, 1994, Orlando, Florida, United States
• 19: Willemain, T. R. and P. A. Desautels. 1993. A method to generate autocorrelated uniform random numbers. Journal of Statistical Computation and Simulation 45:23-31.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.6 SIMULATION AND MODELING
      I.6.1 Simulation Theory
          Subjects: Model classification

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

General Terms:
Experimentation, Theory