Comparing computer experiments for fitting high-order polynomial metamodels

Rachel T. Johnson, Douglas Montgomery, Bradley Jones, Peter A. Parker

Research output: Contribution to journalArticle

14 Scopus citations

Abstract

The use of simulation as a modeling and analysis tool is wide spread. Simulation is an enabling tool for experimenting virtually on a validated computer environment. Often the underlying function for a computer experiment result has too much curvature to be adequately modeled by a low-order polynomial. In such cases, finding an appropriate experimental design is not easy. We evaluate several computer experiments assuming the modeler is interested in fitting a high-order polynomial to the response data considering both optimal and space-filling designs. We also introduce a new class of hybrid designs that can be used for deterministic or stochastic simulation models.

Original languageEnglish (US)
Pages (from-to)86-102
Number of pages17
JournalJournal of Quality Technology
Volume42
Issue number1
DOIs
StatePublished - Jan 2010

    Fingerprint

Keywords

  • Optimal Designd
  • Response Surface
  • Space-Filling Design

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this