Variable selection for kriging in computer experiments

Hengzhen Huang, Dennis K.J. Lin, Min Qian Liu, Qiaozhen Zhang

Research output: Contribution to journalArticle

Abstract

An efficient variable selection technique for kriging in computer experiments is proposed. Kriging models are popularly used in the analysis of computer experiments. The conventional kriging models, the ordinary kriging, and universal kriging could lead to poor prediction performance because of their prespecified mean functions. Identifying an appropriate mean function for kriging is a critical issue. In this article, we develop a Bayesian variable-selection method for the mean function and the performance of the proposed method can be guaranteed by the convergence property of Gibbs sampler. A real-life application on piston design from the computer experiment literature is used to illustrate its implementation. The usefulness of the proposed method is demonstrated via the practical example and some simulative studies. It is shown that the proposed method compares favorably with the existing methods and performs satisfactorily in terms of several important measurements relevant to variable selection and prediction accuracy.

Original languageEnglish (US)
Pages (from-to)40-53
Number of pages14
JournalJournal of Quality Technology
Volume52
Issue number1
DOIs
StatePublished - Jan 2 2020

Fingerprint

Experiments
Pistons
Variable selection
Kriging
Computer experiments
Prediction
Prediction accuracy
Usefulness
Gibbs sampler

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Huang, Hengzhen ; Lin, Dennis K.J. ; Liu, Min Qian ; Zhang, Qiaozhen. / Variable selection for kriging in computer experiments. In: Journal of Quality Technology. 2020 ; Vol. 52, No. 1. pp. 40-53.
@article{651dbc933a104237a6077dfd90f9df16,
title = "Variable selection for kriging in computer experiments",
abstract = "An efficient variable selection technique for kriging in computer experiments is proposed. Kriging models are popularly used in the analysis of computer experiments. The conventional kriging models, the ordinary kriging, and universal kriging could lead to poor prediction performance because of their prespecified mean functions. Identifying an appropriate mean function for kriging is a critical issue. In this article, we develop a Bayesian variable-selection method for the mean function and the performance of the proposed method can be guaranteed by the convergence property of Gibbs sampler. A real-life application on piston design from the computer experiment literature is used to illustrate its implementation. The usefulness of the proposed method is demonstrated via the practical example and some simulative studies. It is shown that the proposed method compares favorably with the existing methods and performs satisfactorily in terms of several important measurements relevant to variable selection and prediction accuracy.",
author = "Hengzhen Huang and Lin, {Dennis K.J.} and Liu, {Min Qian} and Qiaozhen Zhang",
year = "2020",
month = "1",
day = "2",
doi = "10.1080/00224065.2019.1569959",
language = "English (US)",
volume = "52",
pages = "40--53",
journal = "Journal of Quality Technology",
issn = "0022-4065",
publisher = "American Society for Quality",
number = "1",

}

Variable selection for kriging in computer experiments. / Huang, Hengzhen; Lin, Dennis K.J.; Liu, Min Qian; Zhang, Qiaozhen.

In: Journal of Quality Technology, Vol. 52, No. 1, 02.01.2020, p. 40-53.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Variable selection for kriging in computer experiments

AU - Huang, Hengzhen

AU - Lin, Dennis K.J.

AU - Liu, Min Qian

AU - Zhang, Qiaozhen

PY - 2020/1/2

Y1 - 2020/1/2

N2 - An efficient variable selection technique for kriging in computer experiments is proposed. Kriging models are popularly used in the analysis of computer experiments. The conventional kriging models, the ordinary kriging, and universal kriging could lead to poor prediction performance because of their prespecified mean functions. Identifying an appropriate mean function for kriging is a critical issue. In this article, we develop a Bayesian variable-selection method for the mean function and the performance of the proposed method can be guaranteed by the convergence property of Gibbs sampler. A real-life application on piston design from the computer experiment literature is used to illustrate its implementation. The usefulness of the proposed method is demonstrated via the practical example and some simulative studies. It is shown that the proposed method compares favorably with the existing methods and performs satisfactorily in terms of several important measurements relevant to variable selection and prediction accuracy.

AB - An efficient variable selection technique for kriging in computer experiments is proposed. Kriging models are popularly used in the analysis of computer experiments. The conventional kriging models, the ordinary kriging, and universal kriging could lead to poor prediction performance because of their prespecified mean functions. Identifying an appropriate mean function for kriging is a critical issue. In this article, we develop a Bayesian variable-selection method for the mean function and the performance of the proposed method can be guaranteed by the convergence property of Gibbs sampler. A real-life application on piston design from the computer experiment literature is used to illustrate its implementation. The usefulness of the proposed method is demonstrated via the practical example and some simulative studies. It is shown that the proposed method compares favorably with the existing methods and performs satisfactorily in terms of several important measurements relevant to variable selection and prediction accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85068173541&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068173541&partnerID=8YFLogxK

U2 - 10.1080/00224065.2019.1569959

DO - 10.1080/00224065.2019.1569959

M3 - Article

AN - SCOPUS:85068173541

VL - 52

SP - 40

EP - 53

JO - Journal of Quality Technology

JF - Journal of Quality Technology

SN - 0022-4065

IS - 1

ER -