Home > Research > Publications & Outputs > The effects of common random numbers on stochas...

Research

Links

Text available via DOI:

View graph of relations

The effects of common random numbers on stochastic kriging metamodels

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

The effects of common random numbers on stochastic kriging metamodels. / Chen, Xi; Ankenman, Bruce E.; Nelson, Barry L.
In: ACM Transactions on Modeling and Computer Simulation, Vol. 22, No. 2, 7, 03.2012, p. 1-20.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Chen, X, Ankenman, BE & Nelson, BL 2012, 'The effects of common random numbers on stochastic kriging metamodels', ACM Transactions on Modeling and Computer Simulation, vol. 22, no. 2, 7, pp. 1-20. https://doi.org/10.1145/2133390.2133391

APA

Chen, X., Ankenman, B. E., & Nelson, B. L. (2012). The effects of common random numbers on stochastic kriging metamodels. ACM Transactions on Modeling and Computer Simulation, 22(2), 1-20. Article 7. https://doi.org/10.1145/2133390.2133391

Vancouver

Chen X, Ankenman BE, Nelson BL. The effects of common random numbers on stochastic kriging metamodels. ACM Transactions on Modeling and Computer Simulation. 2012 Mar;22(2):1-20. 7. doi: 10.1145/2133390.2133391

Author

Chen, Xi ; Ankenman, Bruce E. ; Nelson, Barry L. / The effects of common random numbers on stochastic kriging metamodels. In: ACM Transactions on Modeling and Computer Simulation. 2012 ; Vol. 22, No. 2. pp. 1-20.

Bibtex

@article{53a548b9e55c4063b98ab97aaf114324,
title = "The effects of common random numbers on stochastic kriging metamodels",
abstract = "Ankenman et al. introduced stochastic kriging as a metamodeling tool for representing stochastic simulation response surfaces, and employed a very simple example to suggest that the use of Common Random Numbers (CRN) degrades the capability of stochastic kriging to predict the true response surface. In this article we undertake an in-depth analysis of the interaction between CRN and stochastic kriging by analyzing a richer collection of models; in particular, we consider stochastic kriging models with a linear trend term. We also perform an empirical study of the effect of CRN on stochastic kriging. We also consider the effect of CRN on metamodel parameter estimation and response-surface gradient estimation, as well as response-surface prediction. In brief, we confirm that CRN is detrimental to prediction, but show that it leads to better estimation of slope parameters and superior gradient estimation compared to independent simulation.",
author = "Xi Chen and Ankenman, {Bruce E.} and Nelson, {Barry L.}",
year = "2012",
month = mar,
doi = "10.1145/2133390.2133391",
language = "English",
volume = "22",
pages = "1--20",
journal = "ACM Transactions on Modeling and Computer Simulation",
issn = "1049-3301",
publisher = "Association for Computing Machinery (ACM)",
number = "2",

}

RIS

TY - JOUR

T1 - The effects of common random numbers on stochastic kriging metamodels

AU - Chen, Xi

AU - Ankenman, Bruce E.

AU - Nelson, Barry L.

PY - 2012/3

Y1 - 2012/3

N2 - Ankenman et al. introduced stochastic kriging as a metamodeling tool for representing stochastic simulation response surfaces, and employed a very simple example to suggest that the use of Common Random Numbers (CRN) degrades the capability of stochastic kriging to predict the true response surface. In this article we undertake an in-depth analysis of the interaction between CRN and stochastic kriging by analyzing a richer collection of models; in particular, we consider stochastic kriging models with a linear trend term. We also perform an empirical study of the effect of CRN on stochastic kriging. We also consider the effect of CRN on metamodel parameter estimation and response-surface gradient estimation, as well as response-surface prediction. In brief, we confirm that CRN is detrimental to prediction, but show that it leads to better estimation of slope parameters and superior gradient estimation compared to independent simulation.

AB - Ankenman et al. introduced stochastic kriging as a metamodeling tool for representing stochastic simulation response surfaces, and employed a very simple example to suggest that the use of Common Random Numbers (CRN) degrades the capability of stochastic kriging to predict the true response surface. In this article we undertake an in-depth analysis of the interaction between CRN and stochastic kriging by analyzing a richer collection of models; in particular, we consider stochastic kriging models with a linear trend term. We also perform an empirical study of the effect of CRN on stochastic kriging. We also consider the effect of CRN on metamodel parameter estimation and response-surface gradient estimation, as well as response-surface prediction. In brief, we confirm that CRN is detrimental to prediction, but show that it leads to better estimation of slope parameters and superior gradient estimation compared to independent simulation.

U2 - 10.1145/2133390.2133391

DO - 10.1145/2133390.2133391

M3 - Journal article

VL - 22

SP - 1

EP - 20

JO - ACM Transactions on Modeling and Computer Simulation

JF - ACM Transactions on Modeling and Computer Simulation

SN - 1049-3301

IS - 2

M1 - 7

ER -