Exclusive Content & Downloads from ASQ

Choosing the Sample Size of a Computer Experiment - A Practical Guide

Summary: [This abstract is based on the authors' abstract.] Evidence is given supporting the informal rule regarding the number of runs needed for an effective initial computer experiment. Two key characteristics of computer codes that affect sample size are quantified: the total sensitivity of a code output variable to input variables and the manner in which this sensitivity is distributed across the input variables. Both measures relate to the correlation structure in the Gaussian process approximation of the code. A simulation study and specific codes modeling climate and ligand activation of G-protein support the arguments.

Anyone with a subscription, including Site and Enterprise members, can access this article.

Other Ways to Access content:

Join ASQ

Join ASQ as a Full member. Enjoy all the ASQ member benefits including access to many online articles.

  • Topics: Sampling
  • Keywords: Computer models, Dimensional measurement, Gaussian curve, Latin squares, Prediction, Randomization tests
  • Author: Loeppky, Jason L.; Sacks, Jerome; Welch, William J.
  • Journal: Technometrics