Steady-state simulation analysis using ASAP3

  • Authors:

  • Natalie M. Steiger;Emily K. Lada;James R. Wilson;Jeffrey A. Joines;Christos Alexopoulos;David Goldsman

  • Affiliations:

  • University of Maine, Orono, ME;Statistical and Applied Mathematical Sciences Institute, Research Triangle Park, NC;North Carolina State University, Raleigh, NC;North Carolina State University, Raleigh, NC;Georgia Institute of Technology, Atlanta, GA;Georgia Institute of Technology, Atlanta, GA

  • Venue:
  • WSC '04 Proceedings of the 36th conference on Winter simulation
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

We discuss ASAP3, a refinement of the batch means algorithms ASAP and ASAP2. ASAP3 is a sequential procedure designed to produce a confidence-interval estimator for the expected response of a steady-state simulation that satisfies user-specified precision and coverage-probability requirements. ASAP3 operates as follows: the batch size is increased until the batch means pass the Shapiro-Wilk test for multivariate normality; and then ASAP3 fits a first-order autoregressive (AR(1)) time series model to the batch means. If necessary, the batch size is further increased until the autoregressive parameter in the AR(1) model does not significantly exceed 0.8. Next ASAP3 computes the terms of an inverse Cornish-Fisher expansion for the classical batch means t-ratio based on the AR(1) parameter estimates; and finally ASAP3 delivers a correlation-adjusted confidence interval based on this expansion. ASAP3 compared favorably with other batch means procedures (namely, ABATCH, ASAP, ASAP2, and LBATCH) in an extensive experimental performance evaluation.