Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations

Robert M. Itami, Darrel Zell, Frank Grigel, Randy Gimblett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

A standard problem in the analysis of outputs from terminating simulations is the need to determine the number of replications needed to construct confidence intervals for performance indicators from the simulation (Law and Kelton, 2000). In traditional industrial applications of simulation such as manufacturing and queuing simulations a single mean for each performance indicator is all that is needed. In spatial simulations however, the problem is more complex as performance indicators can vary spatially as in the case of travel simulations where performance indicators for each destination must be analysed. This paper presents three alternative methods recommended in the simulation literature for determining the number of replications required to obtain confidence intervals based for a given alpha level and user defined confidence interval half width or relative preceision. The problem of measuring multiple performance indicators is addressed with a short discussion of the Bonferroni Correction. These methods are then adapted to spatial simulations using a travel simulation for Banff, Yoho, Kootenay and Jasper National Parks as an example. Outputs for daily link Use and daily link encounters are examined applying different values for absolute accuracy and relative precision. Conclusions are then drawn on the relationship between the sensitivity of performance indicators to random variables in the simulation model and the specification of absolute accuracy and relative precision for spatial dynamic simulation models.

Original languageEnglish (US)
Title of host publicationMODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings
Pages141-148
Number of pages8
StatePublished - 2005
EventInternational Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, MODSIM05 - Melbourne, VIC, Australia
Duration: Dec 12 2005Dec 15 2005

Other

OtherInternational Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, MODSIM05
CountryAustralia
CityMelbourne, VIC
Period12/12/0512/15/05

Fingerprint

Replication
Confidence interval
Performance Indicators
Random variables
Industrial applications
Simulation
Specifications
Relative Precision
Computer simulation
Simulation Model
Bonferroni
Queuing
Output
Industrial Application
Dynamic Simulation
Performance indicators
Dynamic Model
Manufacturing
Random variable
Vary

Keywords

  • Simulation output analysis
  • Simulation statistics
  • Spatial simulation

ASJC Scopus subject areas

  • Information Systems and Management
  • Modeling and Simulation

Cite this

Itami, R. M., Zell, D., Grigel, F., & Gimblett, R. (2005). Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations. In MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings (pp. 141-148)

Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations. / Itami, Robert M.; Zell, Darrel; Grigel, Frank; Gimblett, Randy.

MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings. 2005. p. 141-148.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Itami, RM, Zell, D, Grigel, F & Gimblett, R 2005, Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations. in MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings. pp. 141-148, International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, MODSIM05, Melbourne, VIC, Australia, 12/12/05.
Itami RM, Zell D, Grigel F, Gimblett R. Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations. In MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings. 2005. p. 141-148
Itami, Robert M. ; Zell, Darrel ; Grigel, Frank ; Gimblett, Randy. / Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations. MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings. 2005. pp. 141-148
@inproceedings{ab49ec1ea9c842aca531de60466c6940,
title = "Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations",
abstract = "A standard problem in the analysis of outputs from terminating simulations is the need to determine the number of replications needed to construct confidence intervals for performance indicators from the simulation (Law and Kelton, 2000). In traditional industrial applications of simulation such as manufacturing and queuing simulations a single mean for each performance indicator is all that is needed. In spatial simulations however, the problem is more complex as performance indicators can vary spatially as in the case of travel simulations where performance indicators for each destination must be analysed. This paper presents three alternative methods recommended in the simulation literature for determining the number of replications required to obtain confidence intervals based for a given alpha level and user defined confidence interval half width or relative preceision. The problem of measuring multiple performance indicators is addressed with a short discussion of the Bonferroni Correction. These methods are then adapted to spatial simulations using a travel simulation for Banff, Yoho, Kootenay and Jasper National Parks as an example. Outputs for daily link Use and daily link encounters are examined applying different values for absolute accuracy and relative precision. Conclusions are then drawn on the relationship between the sensitivity of performance indicators to random variables in the simulation model and the specification of absolute accuracy and relative precision for spatial dynamic simulation models.",
keywords = "Simulation output analysis, Simulation statistics, Spatial simulation",
author = "Itami, {Robert M.} and Darrel Zell and Frank Grigel and Randy Gimblett",
year = "2005",
language = "English (US)",
isbn = "0975840002",
pages = "141--148",
booktitle = "MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings",

}

TY - GEN

T1 - Generating confidence intervals for spatial simulations - Determining the number of replications for spatial terminating simulations

AU - Itami, Robert M.

AU - Zell, Darrel

AU - Grigel, Frank

AU - Gimblett, Randy

PY - 2005

Y1 - 2005

N2 - A standard problem in the analysis of outputs from terminating simulations is the need to determine the number of replications needed to construct confidence intervals for performance indicators from the simulation (Law and Kelton, 2000). In traditional industrial applications of simulation such as manufacturing and queuing simulations a single mean for each performance indicator is all that is needed. In spatial simulations however, the problem is more complex as performance indicators can vary spatially as in the case of travel simulations where performance indicators for each destination must be analysed. This paper presents three alternative methods recommended in the simulation literature for determining the number of replications required to obtain confidence intervals based for a given alpha level and user defined confidence interval half width or relative preceision. The problem of measuring multiple performance indicators is addressed with a short discussion of the Bonferroni Correction. These methods are then adapted to spatial simulations using a travel simulation for Banff, Yoho, Kootenay and Jasper National Parks as an example. Outputs for daily link Use and daily link encounters are examined applying different values for absolute accuracy and relative precision. Conclusions are then drawn on the relationship between the sensitivity of performance indicators to random variables in the simulation model and the specification of absolute accuracy and relative precision for spatial dynamic simulation models.

AB - A standard problem in the analysis of outputs from terminating simulations is the need to determine the number of replications needed to construct confidence intervals for performance indicators from the simulation (Law and Kelton, 2000). In traditional industrial applications of simulation such as manufacturing and queuing simulations a single mean for each performance indicator is all that is needed. In spatial simulations however, the problem is more complex as performance indicators can vary spatially as in the case of travel simulations where performance indicators for each destination must be analysed. This paper presents three alternative methods recommended in the simulation literature for determining the number of replications required to obtain confidence intervals based for a given alpha level and user defined confidence interval half width or relative preceision. The problem of measuring multiple performance indicators is addressed with a short discussion of the Bonferroni Correction. These methods are then adapted to spatial simulations using a travel simulation for Banff, Yoho, Kootenay and Jasper National Parks as an example. Outputs for daily link Use and daily link encounters are examined applying different values for absolute accuracy and relative precision. Conclusions are then drawn on the relationship between the sensitivity of performance indicators to random variables in the simulation model and the specification of absolute accuracy and relative precision for spatial dynamic simulation models.

KW - Simulation output analysis

KW - Simulation statistics

KW - Spatial simulation

UR - http://www.scopus.com/inward/record.url?scp=80053095804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053095804&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0975840002

SN - 9780975840009

SP - 141

EP - 148

BT - MODSIM05 - International Congress on Modelling and Simulation: Advances and Applications for Management and Decision Making, Proceedings

ER -