Bootstrap Confidence Intervals for Simulation Output Parameters

Russell R. Barton; Luke A. Rhodes-Leader

doi:10.1109/WSC60868.2023.10407467

Bootstrap Confidence Intervals for Simulation Output Parameters

Russell R. Barton, Luke A. Rhodes-Leader

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Bootstrapping has been used to characterize the impact on discrete-event simulation output arising from input model uncertainty for thirty years. The distribution of simulation output statistics can be very non-normal, especially in simulation of heavily loaded queueing systems, and systems operating at a near optimal value of the output measure. This paper presents issues facing simulationists in using bootstrapping to provide confidence intervals for parameters related to the distribution of simulation output statistics, and identifies appropriate alternatives to the basic and percentile bootstrap methods. Both input uncertainty and ordinary output analysis settings are included.

Original language	English (US)
Title of host publication	2023 Winter Simulation Conference, WSC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	421-432
Number of pages	12
ISBN (Electronic)	9798350369663
DOIs	https://doi.org/10.1109/WSC60868.2023.10407467
State	Published - 2023
Event	2023 Winter Simulation Conference, WSC 2023 - San Antonio, United States Duration: Dec 10 2023 → Dec 13 2023

Publication series

Name	Proceedings - Winter Simulation Conference
ISSN (Print)	0891-7736

Conference

Conference	2023 Winter Simulation Conference, WSC 2023
Country/Territory	United States
City	San Antonio
Period	12/10/23 → 12/13/23

All Science Journal Classification (ASJC) codes

Software
Modeling and Simulation
Computer Science Applications

Access to Document

10.1109/WSC60868.2023.10407467

Cite this

@inproceedings{f541c517454941f88487cad68a7a7eda,

title = "Bootstrap Confidence Intervals for Simulation Output Parameters",

abstract = "Bootstrapping has been used to characterize the impact on discrete-event simulation output arising from input model uncertainty for thirty years. The distribution of simulation output statistics can be very non-normal, especially in simulation of heavily loaded queueing systems, and systems operating at a near optimal value of the output measure. This paper presents issues facing simulationists in using bootstrapping to provide confidence intervals for parameters related to the distribution of simulation output statistics, and identifies appropriate alternatives to the basic and percentile bootstrap methods. Both input uncertainty and ordinary output analysis settings are included.",

author = "Barton, {Russell R.} and Rhodes-Leader, {Luke A.}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 Winter Simulation Conference, WSC 2023 ; Conference date: 10-12-2023 Through 13-12-2023",

year = "2023",

doi = "10.1109/WSC60868.2023.10407467",

language = "English (US)",

series = "Proceedings - Winter Simulation Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "421--432",

booktitle = "2023 Winter Simulation Conference, WSC 2023",

address = "United States",

}

Barton, RR & Rhodes-Leader, LA 2023, Bootstrap Confidence Intervals for Simulation Output Parameters. in 2023 Winter Simulation Conference, WSC 2023. Proceedings - Winter Simulation Conference, Institute of Electrical and Electronics Engineers Inc., pp. 421-432, 2023 Winter Simulation Conference, WSC 2023, San Antonio, United States, 12/10/23. https://doi.org/10.1109/WSC60868.2023.10407467

TY - GEN

T1 - Bootstrap Confidence Intervals for Simulation Output Parameters

AU - Barton, Russell R.

AU - Rhodes-Leader, Luke A.

PY - 2023

Y1 - 2023

N2 - Bootstrapping has been used to characterize the impact on discrete-event simulation output arising from input model uncertainty for thirty years. The distribution of simulation output statistics can be very non-normal, especially in simulation of heavily loaded queueing systems, and systems operating at a near optimal value of the output measure. This paper presents issues facing simulationists in using bootstrapping to provide confidence intervals for parameters related to the distribution of simulation output statistics, and identifies appropriate alternatives to the basic and percentile bootstrap methods. Both input uncertainty and ordinary output analysis settings are included.

AB - Bootstrapping has been used to characterize the impact on discrete-event simulation output arising from input model uncertainty for thirty years. The distribution of simulation output statistics can be very non-normal, especially in simulation of heavily loaded queueing systems, and systems operating at a near optimal value of the output measure. This paper presents issues facing simulationists in using bootstrapping to provide confidence intervals for parameters related to the distribution of simulation output statistics, and identifies appropriate alternatives to the basic and percentile bootstrap methods. Both input uncertainty and ordinary output analysis settings are included.

UR - http://www.scopus.com/inward/record.url?scp=85185383803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85185383803&partnerID=8YFLogxK

U2 - 10.1109/WSC60868.2023.10407467

DO - 10.1109/WSC60868.2023.10407467

M3 - Conference contribution

AN - SCOPUS:85185383803

T3 - Proceedings - Winter Simulation Conference

SP - 421

EP - 432

BT - 2023 Winter Simulation Conference, WSC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 Winter Simulation Conference, WSC 2023

Y2 - 10 December 2023 through 13 December 2023

ER -

Bootstrap Confidence Intervals for Simulation Output Parameters

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this