18 Citations (Scopus)

Abstract

We introduce a new algorithm for generating near G-optimal designs for second-order models over cuboidal regions. The algorithm involves the use of Brent's minimization algorithm with coordinate exchange to create designs for 2 to 5 factors. Designs created using this new method either match or exceed the G-efficiency of previously reported designs. We also introduce a new graphical tool, the variance ratio fraction of design space (VRFDS) plot, which is useful for easy comparison of the prediction variance for competing designs over a given region of interest. Using the VRFDS plot to compare G-optimal designs to I-optimal designs shows that the G-optimal designs have higher prediction variance over the vast majority of the design region. This suggests that, for many response surface studies, G-optimal designs may not be the best choice.

Original languageEnglish (US)
Pages (from-to)3-20
Number of pages18
JournalJournal of Quality Technology
Volume42
Issue number1
StatePublished - Jan 2010

Fingerprint

Optimal design
Prediction
Variance ratio
Factors
Response surface

Keywords

  • Computer-generated designs
  • D-efficiency
  • Fraction of design space plots
  • G-efficiency
  • I-efficiency
  • Optimality criteria
  • Prediction variance

ASJC Scopus subject areas

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

Cite this

Rodríguez, M., Jones, B., Borror, C. M., & Montgomery, D. (2010). Generating and assessing exact G-optimal designs. Journal of Quality Technology, 42(1), 3-20.

Generating and assessing exact G-optimal designs. / Rodríguez, Myrta; Jones, Bradley; Borror, Connie M.; Montgomery, Douglas.

In: Journal of Quality Technology, Vol. 42, No. 1, 01.2010, p. 3-20.

Research output: Contribution to journalArticle

Rodríguez, M, Jones, B, Borror, CM & Montgomery, D 2010, 'Generating and assessing exact G-optimal designs', Journal of Quality Technology, vol. 42, no. 1, pp. 3-20.
Rodríguez, Myrta ; Jones, Bradley ; Borror, Connie M. ; Montgomery, Douglas. / Generating and assessing exact G-optimal designs. In: Journal of Quality Technology. 2010 ; Vol. 42, No. 1. pp. 3-20.
@article{1bd57095bd1b4c649d496021fbeac91f,
title = "Generating and assessing exact G-optimal designs",
abstract = "We introduce a new algorithm for generating near G-optimal designs for second-order models over cuboidal regions. The algorithm involves the use of Brent's minimization algorithm with coordinate exchange to create designs for 2 to 5 factors. Designs created using this new method either match or exceed the G-efficiency of previously reported designs. We also introduce a new graphical tool, the variance ratio fraction of design space (VRFDS) plot, which is useful for easy comparison of the prediction variance for competing designs over a given region of interest. Using the VRFDS plot to compare G-optimal designs to I-optimal designs shows that the G-optimal designs have higher prediction variance over the vast majority of the design region. This suggests that, for many response surface studies, G-optimal designs may not be the best choice.",
keywords = "Computer-generated designs, D-efficiency, Fraction of design space plots, G-efficiency, I-efficiency, Optimality criteria, Prediction variance",
author = "Myrta Rodr{\'i}guez and Bradley Jones and Borror, {Connie M.} and Douglas Montgomery",
year = "2010",
month = "1",
language = "English (US)",
volume = "42",
pages = "3--20",
journal = "Journal of Quality Technology",
issn = "0022-4065",
publisher = "American Society for Quality",
number = "1",

}

TY - JOUR

T1 - Generating and assessing exact G-optimal designs

AU - Rodríguez, Myrta

AU - Jones, Bradley

AU - Borror, Connie M.

AU - Montgomery, Douglas

PY - 2010/1

Y1 - 2010/1

N2 - We introduce a new algorithm for generating near G-optimal designs for second-order models over cuboidal regions. The algorithm involves the use of Brent's minimization algorithm with coordinate exchange to create designs for 2 to 5 factors. Designs created using this new method either match or exceed the G-efficiency of previously reported designs. We also introduce a new graphical tool, the variance ratio fraction of design space (VRFDS) plot, which is useful for easy comparison of the prediction variance for competing designs over a given region of interest. Using the VRFDS plot to compare G-optimal designs to I-optimal designs shows that the G-optimal designs have higher prediction variance over the vast majority of the design region. This suggests that, for many response surface studies, G-optimal designs may not be the best choice.

AB - We introduce a new algorithm for generating near G-optimal designs for second-order models over cuboidal regions. The algorithm involves the use of Brent's minimization algorithm with coordinate exchange to create designs for 2 to 5 factors. Designs created using this new method either match or exceed the G-efficiency of previously reported designs. We also introduce a new graphical tool, the variance ratio fraction of design space (VRFDS) plot, which is useful for easy comparison of the prediction variance for competing designs over a given region of interest. Using the VRFDS plot to compare G-optimal designs to I-optimal designs shows that the G-optimal designs have higher prediction variance over the vast majority of the design region. This suggests that, for many response surface studies, G-optimal designs may not be the best choice.

KW - Computer-generated designs

KW - D-efficiency

KW - Fraction of design space plots

KW - G-efficiency

KW - I-efficiency

KW - Optimality criteria

KW - Prediction variance

UR - http://www.scopus.com/inward/record.url?scp=79951929184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951929184&partnerID=8YFLogxK

M3 - Article

VL - 42

SP - 3

EP - 20

JO - Journal of Quality Technology

JF - Journal of Quality Technology

SN - 0022-4065

IS - 1

ER -