Input uncertainty in stochastic simulations in the presence of dependent discrete input variables

A. Akcay, B. Biller

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

1 Citaat (Scopus)

Uittreksel

This paper considers stochastic simulations with correlated input random variables having NORmal-To-Anything (NORTA) distributions. We assume that the simulation analyst does not know the marginal distribution functions and the base correlation matrix of the NORTA distribution but has access to a finite amount of input data for statistical inference. We propose a Bayesian procedure that decouples the input model estimation into two stages and overcomes the problem of inconsistently estimating the base correlation matrix of the NORTA distribution in the presence of discrete input variables. It further allows us to estimate the variability of the simulation output data that are attributable to the input uncertainty due to not knowing the NORTA distribution. Using this input uncertainty estimate, we introduce a simple yet effective method to obtain input uncertainty adjusted credible intervals. We illustrate our method in an assemble-to-order production system with a correlated demand arrival process.

TaalEngels
Pagina's295-306
TijdschriftJournal of Simulation
Volume12
Nummer van het tijdschrift4
Vroegere onlinedatum14 dec 2017
DOI's
StatusGepubliceerd - 2018

Vingerafdruk

Stochastic Simulation
Uncertainty
Dependent
Correlation Matrix
Credible Interval
Random variables
Marginal Function
Distribution functions
Production Systems
Marginal Distribution
Statistical Inference
Estimate
Distribution Function
Simulation
Random variable
Output
Model

Citeer dit

@article{d0e830f20c984a59a6ca1b186e7c2c43,
title = "Input uncertainty in stochastic simulations in the presence of dependent discrete input variables",
abstract = "This paper considers stochastic simulations with correlated input random variables having NORmal-To-Anything (NORTA) distributions. We assume that the simulation analyst does not know the marginal distribution functions and the base correlation matrix of the NORTA distribution but has access to a finite amount of input data for statistical inference. We propose a Bayesian procedure that decouples the input model estimation into two stages and overcomes the problem of inconsistently estimating the base correlation matrix of the NORTA distribution in the presence of discrete input variables. It further allows us to estimate the variability of the simulation output data that are attributable to the input uncertainty due to not knowing the NORTA distribution. Using this input uncertainty estimate, we introduce a simple yet effective method to obtain input uncertainty adjusted credible intervals. We illustrate our method in an assemble-to-order production system with a correlated demand arrival process.",
author = "A. Akcay and B. Biller",
year = "2018",
doi = "10.1057/s41273-017-0051-3",
language = "English",
volume = "12",
pages = "295--306",
journal = "Journal of Simulation",
issn = "1747-7778",
publisher = "Palgrave Macmillan Ltd.",
number = "4",

}

Input uncertainty in stochastic simulations in the presence of dependent discrete input variables. / Akcay, A.; Biller, B.

In: Journal of Simulation, Vol. 12, Nr. 4, 2018, blz. 295-306.

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

TY - JOUR

T1 - Input uncertainty in stochastic simulations in the presence of dependent discrete input variables

AU - Akcay,A.

AU - Biller,B.

PY - 2018

Y1 - 2018

N2 - This paper considers stochastic simulations with correlated input random variables having NORmal-To-Anything (NORTA) distributions. We assume that the simulation analyst does not know the marginal distribution functions and the base correlation matrix of the NORTA distribution but has access to a finite amount of input data for statistical inference. We propose a Bayesian procedure that decouples the input model estimation into two stages and overcomes the problem of inconsistently estimating the base correlation matrix of the NORTA distribution in the presence of discrete input variables. It further allows us to estimate the variability of the simulation output data that are attributable to the input uncertainty due to not knowing the NORTA distribution. Using this input uncertainty estimate, we introduce a simple yet effective method to obtain input uncertainty adjusted credible intervals. We illustrate our method in an assemble-to-order production system with a correlated demand arrival process.

AB - This paper considers stochastic simulations with correlated input random variables having NORmal-To-Anything (NORTA) distributions. We assume that the simulation analyst does not know the marginal distribution functions and the base correlation matrix of the NORTA distribution but has access to a finite amount of input data for statistical inference. We propose a Bayesian procedure that decouples the input model estimation into two stages and overcomes the problem of inconsistently estimating the base correlation matrix of the NORTA distribution in the presence of discrete input variables. It further allows us to estimate the variability of the simulation output data that are attributable to the input uncertainty due to not knowing the NORTA distribution. Using this input uncertainty estimate, we introduce a simple yet effective method to obtain input uncertainty adjusted credible intervals. We illustrate our method in an assemble-to-order production system with a correlated demand arrival process.

UR - http://www.scopus.com/inward/record.url?scp=85013471405&partnerID=8YFLogxK

U2 - 10.1057/s41273-017-0051-3

DO - 10.1057/s41273-017-0051-3

M3 - Article

VL - 12

SP - 295

EP - 306

JO - Journal of Simulation

T2 - Journal of Simulation

JF - Journal of Simulation

SN - 1747-7778

IS - 4

ER -