Validation of correlation-induction strategies for simulation experiments

ABSTRACT

This paper develops a three-stage procedure for validating the use of the Schruben-Margolin correlation Induction strategy together with the follow-up analysis of Nozarl, Arnold, and Pegden in a simulation experiment designed to estimate a general linear model for the simulation response. Each stage of the procedure tests a key assumption about the behavior of the response across all points in the design. The first stage tests for multivariate normality, the second stage tests for the induced covariance structure postulated by Schruben and Margolin, and the third stage tests for the adequacy of the proposed linear model. Because the test in each stage presupposes the properties tested in previous stages, these diagnostic checks on the experimental design and analysis must be performed in the indicated order.

REFERENCES

• 1: Schruben, L.W. and M~rgolln, B.H., "Pseudorandom Number Assignment In Statistically Designed Slmulatlon and Distribution Sampling Experiments,'" Journal of American Statistical Association, 73, i978, 504-525.
• 2: Schruben, L.W., "Designing Correlation Induction Strategies for Simulation Experiments," Chapter 16 in Current Issues in Computer Simulation, Academic Press, New York, 1979, 235-255.
• 3: Nozarl, A., Arnold, S.F., and Pegden, C.D. "Statistical Analysis Under Schruben and Margolln Correlation Induction Strategy," Technical Report, School of Industrial Engineering, University of Oklahoma, 1984.
• 4: Box, G.E., Hunter, W.G., ~nd Hunter, J.S., Statistics for Experimenters" An Introduction to Design, Data Analysis, and Model Building, John Wlley g~ Sons, New York, 1978, 231-241.
• 5: Roys~on, J., "Algorithm AS 181. The W Test for Normallty,'" Applied Statistics, 31, 1982, 176-180.
• 6: Malkovlch, J.F., "'Tests for Multivariate NormalIty," Unpublished Ph.D. Dissertation, University of California, Los Angeles, 1971.
• 7: Malkovlch, J.F. and Aflfl, i.i., "On Tests for Multivariate Normality," Journal of the American Statistical Association, 68, 1973, 176-179.
• 8: Royston, J., "Some Techniques for Assessing Multivariate Normality Based on the Shaplro-WIlk W," Applied Statistics, 32, 1983, 121-133.
• 9: Wllks, S.S., Malhematical Statistics, John Wiley & Sons, New York, 1962, 419-422.