Model selection for analysis of uniform design and computer experiment

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In this paper, a new variable selection procedure is introduced for the analysis of uniform design and computer experiment. The new procedure is distinguished from the traditional ones in such a way that it deletes insignificant variables and estimates the coefficients of significant variables simultaneously. The new procedure has an oracle property (Fan and Li8). It is better than the best subset variable selection in terms of computational cost and model stability. It is superior to the stepwise regression because it does not ignore stochastic errors during the course of selecting variables. The proposed procedure is illustrated by two examples, one is a typical example of uniform design, and the other one is a classical example for computer experiment.

Original languageEnglish (US)
Pages (from-to)367-382
Number of pages16
JournalInternational Journal of Reliability, Quality and Safety Engineering
Volume9
Issue number4
DOIs
StatePublished - Dec 1 2002

Fingerprint

Fans
Experiments
Costs

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Nuclear Energy and Engineering
  • Safety, Risk, Reliability and Quality
  • Aerospace Engineering
  • Energy Engineering and Power Technology
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Cite this

@article{e8c98e9c73c44e1bb5e6d89ba37d8fa3,
title = "Model selection for analysis of uniform design and computer experiment",
abstract = "In this paper, a new variable selection procedure is introduced for the analysis of uniform design and computer experiment. The new procedure is distinguished from the traditional ones in such a way that it deletes insignificant variables and estimates the coefficients of significant variables simultaneously. The new procedure has an oracle property (Fan and Li8). It is better than the best subset variable selection in terms of computational cost and model stability. It is superior to the stepwise regression because it does not ignore stochastic errors during the course of selecting variables. The proposed procedure is illustrated by two examples, one is a typical example of uniform design, and the other one is a classical example for computer experiment.",
author = "Runze Li",
year = "2002",
month = "12",
day = "1",
doi = "10.1142/S0218539302000901",
language = "English (US)",
volume = "9",
pages = "367--382",
journal = "International Journal of Reliability, Quality and Safety Engineering",
issn = "0218-5393",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "4",

}

Model selection for analysis of uniform design and computer experiment. / Li, Runze.

In: International Journal of Reliability, Quality and Safety Engineering, Vol. 9, No. 4, 01.12.2002, p. 367-382.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Model selection for analysis of uniform design and computer experiment

AU - Li, Runze

PY - 2002/12/1

Y1 - 2002/12/1

N2 - In this paper, a new variable selection procedure is introduced for the analysis of uniform design and computer experiment. The new procedure is distinguished from the traditional ones in such a way that it deletes insignificant variables and estimates the coefficients of significant variables simultaneously. The new procedure has an oracle property (Fan and Li8). It is better than the best subset variable selection in terms of computational cost and model stability. It is superior to the stepwise regression because it does not ignore stochastic errors during the course of selecting variables. The proposed procedure is illustrated by two examples, one is a typical example of uniform design, and the other one is a classical example for computer experiment.

AB - In this paper, a new variable selection procedure is introduced for the analysis of uniform design and computer experiment. The new procedure is distinguished from the traditional ones in such a way that it deletes insignificant variables and estimates the coefficients of significant variables simultaneously. The new procedure has an oracle property (Fan and Li8). It is better than the best subset variable selection in terms of computational cost and model stability. It is superior to the stepwise regression because it does not ignore stochastic errors during the course of selecting variables. The proposed procedure is illustrated by two examples, one is a typical example of uniform design, and the other one is a classical example for computer experiment.

UR - http://www.scopus.com/inward/record.url?scp=0036960975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036960975&partnerID=8YFLogxK

U2 - 10.1142/S0218539302000901

DO - 10.1142/S0218539302000901

M3 - Article

AN - SCOPUS:0036960975

VL - 9

SP - 367

EP - 382

JO - International Journal of Reliability, Quality and Safety Engineering

JF - International Journal of Reliability, Quality and Safety Engineering

SN - 0218-5393

IS - 4

ER -