Simulation Factor Screening Using Harmonic Analysis

In this paper, we provide a quantitative approach to Frequency Domain Methodology (FDM) using harmonic analysis. For a certain class of metamodels, we give the frequency domain hypothesis and develop the corresponding hypothesis test. Minimum simulation model run length information for FDM is provided for a subclass of these metamodels. We discuss factor screening designs to increase the power of the test and illustrate these designs by an example.

• 저널Management Science · 39(12) · 1459–1476
• 토픽Probabilistic and Robust Engineering Design · Statistics, Probability and Uncertainty
• DOI10.1287/mnsc.39.12.1459
• 저자Douglas J. Morrice, Lee W. Schruben