Identifying the important factors in simulation models with many factors

B. Bettonvil, J.P.C. Kleijnen

Research output: Working paperDiscussion paperOther research output

368 Downloads (Pure)

Abstract

Simulation models may have many parameters and input variables (together called factors), while only a few factors are really important (parsimony principle). For such models this paper presents an effective and efficient screening technique to identify and estimate those important factors. The technique extends the classical binary search technique to situations with more than a single important factor. The technique uses a low-order polynomial approximation to the input/output behavior of the simulation model. This approximation may account for interactions among factors. The technique is demonstrated by applying it to a complicated ecological simulation that models the increase of temperatures worldwide.
Original languageEnglish
PublisherUnknown Publisher
Number of pages26
Volume1994-114
Publication statusPublished - 1994

Publication series

NameCentER Discussion Paper
Volume1994-114

Fingerprint

Polynomial approximation
Screening
Temperature

Keywords

  • Simulation Models
  • econometrics

Cite this

Bettonvil, B., & Kleijnen, J. P. C. (1994). Identifying the important factors in simulation models with many factors. (CentER Discussion Paper; Vol. 1994-114). Unknown Publisher.
Bettonvil, B. ; Kleijnen, J.P.C. / Identifying the important factors in simulation models with many factors. Unknown Publisher, 1994. (CentER Discussion Paper).
@techreport{5da4bf9f31264cf9954ff2140dbd8b4c,
title = "Identifying the important factors in simulation models with many factors",
abstract = "Simulation models may have many parameters and input variables (together called factors), while only a few factors are really important (parsimony principle). For such models this paper presents an effective and efficient screening technique to identify and estimate those important factors. The technique extends the classical binary search technique to situations with more than a single important factor. The technique uses a low-order polynomial approximation to the input/output behavior of the simulation model. This approximation may account for interactions among factors. The technique is demonstrated by applying it to a complicated ecological simulation that models the increase of temperatures worldwide.",
keywords = "Simulation Models, econometrics",
author = "B. Bettonvil and J.P.C. Kleijnen",
note = "Pagination: 26",
year = "1994",
language = "English",
volume = "1994-114",
series = "CentER Discussion Paper",
publisher = "Unknown Publisher",
type = "WorkingPaper",
institution = "Unknown Publisher",

}

Bettonvil, B & Kleijnen, JPC 1994 'Identifying the important factors in simulation models with many factors' CentER Discussion Paper, vol. 1994-114, Unknown Publisher.

Identifying the important factors in simulation models with many factors. / Bettonvil, B.; Kleijnen, J.P.C.

Unknown Publisher, 1994. (CentER Discussion Paper; Vol. 1994-114).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Identifying the important factors in simulation models with many factors

AU - Bettonvil, B.

AU - Kleijnen, J.P.C.

N1 - Pagination: 26

PY - 1994

Y1 - 1994

N2 - Simulation models may have many parameters and input variables (together called factors), while only a few factors are really important (parsimony principle). For such models this paper presents an effective and efficient screening technique to identify and estimate those important factors. The technique extends the classical binary search technique to situations with more than a single important factor. The technique uses a low-order polynomial approximation to the input/output behavior of the simulation model. This approximation may account for interactions among factors. The technique is demonstrated by applying it to a complicated ecological simulation that models the increase of temperatures worldwide.

AB - Simulation models may have many parameters and input variables (together called factors), while only a few factors are really important (parsimony principle). For such models this paper presents an effective and efficient screening technique to identify and estimate those important factors. The technique extends the classical binary search technique to situations with more than a single important factor. The technique uses a low-order polynomial approximation to the input/output behavior of the simulation model. This approximation may account for interactions among factors. The technique is demonstrated by applying it to a complicated ecological simulation that models the increase of temperatures worldwide.

KW - Simulation Models

KW - econometrics

M3 - Discussion paper

VL - 1994-114

T3 - CentER Discussion Paper

BT - Identifying the important factors in simulation models with many factors

PB - Unknown Publisher

ER -

Bettonvil B, Kleijnen JPC. Identifying the important factors in simulation models with many factors. Unknown Publisher. 1994. (CentER Discussion Paper).