Experimental Design for Sensitivity Analysis of Simulation Models

Research output: Working paperDiscussion paperOther research output

324 Downloads (Pure)

Abstract

This introductory tutorial gives a survey on the use of statistical designs for what if-or sensitivity analysis in simulation.This analysis uses regression analysis to approximate the input/output transformation that is implied by the simulation model; the resulting regression model is also known as metamodel, response surface, compact model, emulator, etc.Regression analysis gives better results when the simulation experiment is well designed, using classical statistical designs (such as fractional factorials, including 2 k-p designs).These statistical techniques reduce the ad hoc character of simulation; that is, these techniques can make simulation studies give more general results, in less time.
Original languageEnglish
Place of PublicationTilburg
PublisherOperations research
Number of pages8
Volume2001-15
Publication statusPublished - 2001

Publication series

NameCentER Discussion Paper
Volume2001-15

Fingerprint

Experimental design
Sensitivity Analysis
Simulation Model
Regression Analysis
Response Surface
Metamodel
Simulation Experiment
Regression Model
Simulation
Fractional
Simulation Study
Output
Design
Model

Keywords

  • experimental design
  • simulation models
  • sensitivity analysis
  • regression analysis

Cite this

Kleijnen, J. P. C. (2001). Experimental Design for Sensitivity Analysis of Simulation Models. (CentER Discussion Paper; Vol. 2001-15). Tilburg: Operations research.
Kleijnen, J.P.C. / Experimental Design for Sensitivity Analysis of Simulation Models. Tilburg : Operations research, 2001. (CentER Discussion Paper).
@techreport{1c7161451d3441b5b9657b56096f1d7e,
title = "Experimental Design for Sensitivity Analysis of Simulation Models",
abstract = "This introductory tutorial gives a survey on the use of statistical designs for what if-or sensitivity analysis in simulation.This analysis uses regression analysis to approximate the input/output transformation that is implied by the simulation model; the resulting regression model is also known as metamodel, response surface, compact model, emulator, etc.Regression analysis gives better results when the simulation experiment is well designed, using classical statistical designs (such as fractional factorials, including 2 k-p designs).These statistical techniques reduce the ad hoc character of simulation; that is, these techniques can make simulation studies give more general results, in less time.",
keywords = "experimental design, simulation models, sensitivity analysis, regression analysis",
author = "J.P.C. Kleijnen",
note = "Pagination: 8",
year = "2001",
language = "English",
volume = "2001-15",
series = "CentER Discussion Paper",
publisher = "Operations research",
type = "WorkingPaper",
institution = "Operations research",

}

Kleijnen, JPC 2001 'Experimental Design for Sensitivity Analysis of Simulation Models' CentER Discussion Paper, vol. 2001-15, Operations research, Tilburg.

Experimental Design for Sensitivity Analysis of Simulation Models. / Kleijnen, J.P.C.

Tilburg : Operations research, 2001. (CentER Discussion Paper; Vol. 2001-15).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Experimental Design for Sensitivity Analysis of Simulation Models

AU - Kleijnen, J.P.C.

N1 - Pagination: 8

PY - 2001

Y1 - 2001

N2 - This introductory tutorial gives a survey on the use of statistical designs for what if-or sensitivity analysis in simulation.This analysis uses regression analysis to approximate the input/output transformation that is implied by the simulation model; the resulting regression model is also known as metamodel, response surface, compact model, emulator, etc.Regression analysis gives better results when the simulation experiment is well designed, using classical statistical designs (such as fractional factorials, including 2 k-p designs).These statistical techniques reduce the ad hoc character of simulation; that is, these techniques can make simulation studies give more general results, in less time.

AB - This introductory tutorial gives a survey on the use of statistical designs for what if-or sensitivity analysis in simulation.This analysis uses regression analysis to approximate the input/output transformation that is implied by the simulation model; the resulting regression model is also known as metamodel, response surface, compact model, emulator, etc.Regression analysis gives better results when the simulation experiment is well designed, using classical statistical designs (such as fractional factorials, including 2 k-p designs).These statistical techniques reduce the ad hoc character of simulation; that is, these techniques can make simulation studies give more general results, in less time.

KW - experimental design

KW - simulation models

KW - sensitivity analysis

KW - regression analysis

M3 - Discussion paper

VL - 2001-15

T3 - CentER Discussion Paper

BT - Experimental Design for Sensitivity Analysis of Simulation Models

PB - Operations research

CY - Tilburg

ER -

Kleijnen JPC. Experimental Design for Sensitivity Analysis of Simulation Models. Tilburg: Operations research. 2001. (CentER Discussion Paper).