×

Validation of simulation analysis methods for the Schruben-Margolin correlation-induction strategy. (English) Zbl 0745.65094

To analyze simulation experiments performed under the strategy proposed by L. W. Schruben and B. H. Margolin [J. Amer. Statist. Assoc. 73, 504-525 (1978; Zbl 0386.62010)] for assigning random number streams to individual runs, A. Nozari, S. F. Arnold and C. D. Pegden [Oper. Res. 35, 127-139 (1987; Zbl 0633.62027)] developed special statistical methods for estimating a general linear regression model of a selected response variables expressed in terms of design variables (regressors) relevant to the target system.
The paper describes a three-stage procedure for validating the use of these simulation analysis methods. Each stage of the validation procedure tests a key assumption about the behavior of the response across all points in the experimental design. The first stage checks for multivariate normality in the overall set of responses, the second stage checks for the Schruben-Margolin covariance structure among those responses, and the third stage checks for adequacy (goodness of fit) of the user-specified model. A numerical example illustrates the application of this validation procedure.

MSC:

65C99 Probabilistic methods, stochastic differential equations
65C20 Probabilistic models, generic numerical methods in probability and statistics
60K10 Applications of renewal theory (reliability, demand theory, etc.)
62J05 Linear regression; mixed models

Software:

AS 181
PDFBibTeX XMLCite
Full Text: DOI