Design of Experiments: An Overview

Research output: Working paperDiscussion paperOther research output

280 Downloads (Pure)

Abstract

Design Of Experiments (DOE) is needed for experiments with real-life systems, and with either deterministic or random simulation models. This contribution discusses the different types of DOE for these three domains, but focusses on random simulation. DOE may have two goals: sensitivity analysis including factor screening and optimization. This contribution starts with classic DOE including 2k-p and Central Composite designs. Next, it discusses factor screening through Sequential Bifurcation. Then it discusses Kriging including Latin Hyper cube Sampling and sequential designs. It ends with optimization through Generalized Response Surface Methodology and Kriging combined with Mathematical Programming, including Taguchian robust optimization.
Original languageEnglish
Place of PublicationTilburg
PublisherOperations research
Number of pages21
Volume2008-70
Publication statusPublished - 2008

Publication series

NameCentER Discussion Paper
Volume2008-70

Fingerprint

Spatial Analysis
Statistical Factor Analysis

Keywords

  • simulation
  • sensitivity analysis
  • optimization
  • factor screening
  • Kriging
  • RSM
  • Taguchi

Cite this

Kleijnen, J. P. C. (2008). Design of Experiments: An Overview. (CentER Discussion Paper; Vol. 2008-70). Tilburg: Operations research.
Kleijnen, J.P.C. / Design of Experiments : An Overview. Tilburg : Operations research, 2008. (CentER Discussion Paper).
@techreport{e05cfa13127a48c9a5b678e320ade144,
title = "Design of Experiments: An Overview",
abstract = "Design Of Experiments (DOE) is needed for experiments with real-life systems, and with either deterministic or random simulation models. This contribution discusses the different types of DOE for these three domains, but focusses on random simulation. DOE may have two goals: sensitivity analysis including factor screening and optimization. This contribution starts with classic DOE including 2k-p and Central Composite designs. Next, it discusses factor screening through Sequential Bifurcation. Then it discusses Kriging including Latin Hyper cube Sampling and sequential designs. It ends with optimization through Generalized Response Surface Methodology and Kriging combined with Mathematical Programming, including Taguchian robust optimization.",
keywords = "simulation, sensitivity analysis, optimization, factor screening, Kriging, RSM, Taguchi",
author = "J.P.C. Kleijnen",
note = "Subsequently published in Proceedings of the Winter Simulation Conference (book), 2008 Pagination: 21",
year = "2008",
language = "English",
volume = "2008-70",
series = "CentER Discussion Paper",
publisher = "Operations research",
type = "WorkingPaper",
institution = "Operations research",

}

Kleijnen, JPC 2008 'Design of Experiments: An Overview' CentER Discussion Paper, vol. 2008-70, Operations research, Tilburg.

Design of Experiments : An Overview. / Kleijnen, J.P.C.

Tilburg : Operations research, 2008. (CentER Discussion Paper; Vol. 2008-70).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Design of Experiments

T2 - An Overview

AU - Kleijnen, J.P.C.

N1 - Subsequently published in Proceedings of the Winter Simulation Conference (book), 2008 Pagination: 21

PY - 2008

Y1 - 2008

N2 - Design Of Experiments (DOE) is needed for experiments with real-life systems, and with either deterministic or random simulation models. This contribution discusses the different types of DOE for these three domains, but focusses on random simulation. DOE may have two goals: sensitivity analysis including factor screening and optimization. This contribution starts with classic DOE including 2k-p and Central Composite designs. Next, it discusses factor screening through Sequential Bifurcation. Then it discusses Kriging including Latin Hyper cube Sampling and sequential designs. It ends with optimization through Generalized Response Surface Methodology and Kriging combined with Mathematical Programming, including Taguchian robust optimization.

AB - Design Of Experiments (DOE) is needed for experiments with real-life systems, and with either deterministic or random simulation models. This contribution discusses the different types of DOE for these three domains, but focusses on random simulation. DOE may have two goals: sensitivity analysis including factor screening and optimization. This contribution starts with classic DOE including 2k-p and Central Composite designs. Next, it discusses factor screening through Sequential Bifurcation. Then it discusses Kriging including Latin Hyper cube Sampling and sequential designs. It ends with optimization through Generalized Response Surface Methodology and Kriging combined with Mathematical Programming, including Taguchian robust optimization.

KW - simulation

KW - sensitivity analysis

KW - optimization

KW - factor screening

KW - Kriging

KW - RSM

KW - Taguchi

M3 - Discussion paper

VL - 2008-70

T3 - CentER Discussion Paper

BT - Design of Experiments

PB - Operations research

CY - Tilburg

ER -

Kleijnen JPC. Design of Experiments: An Overview. Tilburg: Operations research. 2008. (CentER Discussion Paper).