Fraction of design space plots for examining model robustness

Ayca Ozol-Godfrey, Christine M. Anderson-Cook, Douglas Montgomery

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

When choosing between competing designs, it is typical to specify a design space and model on which to base the comparison. The prediction capabilities of the design, specifically G- and V-efficiency using scaled prediction variance (SPV), are based on this chosen model. After the data are collected and individual effects are tested, some terms may not be significant in the model. In this case, the experimenter likely will decide to use a reduced model, which has only a portion of the terms included that were in the original model for which the design was chosen. This paper presents a graphical method for examining design robustness related to the SPV values using fraction of design space (FDS) plots by comparing designs across a number of potential models in a prespecified model space. The FDS plots show the various distributions of the SPV throughout the design space for different models for a chosen design on the same graph. The methods are demonstrated on several examples for different models and on a variety of design spaces.

Original languageEnglish (US)
Pages (from-to)223-235
Number of pages13
JournalJournal of Quality Technology
Volume37
Issue number3
StatePublished - Jul 2005

Fingerprint

Model Robustness
Prediction Variance
Model
G-design
Design
Robustness
Graphical Methods
Reduced Model
Term
Likely

Keywords

  • Alphabetical Optimality Criteria
  • FDS Plot
  • Mixture Experiments
  • Model Reduction
  • Response Surface Designs
  • Scaled Prediction Variance

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Statistics and Probability
  • Management Science and Operations Research

Cite this

Fraction of design space plots for examining model robustness. / Ozol-Godfrey, Ayca; Anderson-Cook, Christine M.; Montgomery, Douglas.

In: Journal of Quality Technology, Vol. 37, No. 3, 07.2005, p. 223-235.

Research output: Contribution to journalArticle

Ozol-Godfrey, A, Anderson-Cook, CM & Montgomery, D 2005, 'Fraction of design space plots for examining model robustness', Journal of Quality Technology, vol. 37, no. 3, pp. 223-235.
Ozol-Godfrey, Ayca ; Anderson-Cook, Christine M. ; Montgomery, Douglas. / Fraction of design space plots for examining model robustness. In: Journal of Quality Technology. 2005 ; Vol. 37, No. 3. pp. 223-235.
@article{9c8478ede9ed43208d5d10219f5ef9c4,
title = "Fraction of design space plots for examining model robustness",
abstract = "When choosing between competing designs, it is typical to specify a design space and model on which to base the comparison. The prediction capabilities of the design, specifically G- and V-efficiency using scaled prediction variance (SPV), are based on this chosen model. After the data are collected and individual effects are tested, some terms may not be significant in the model. In this case, the experimenter likely will decide to use a reduced model, which has only a portion of the terms included that were in the original model for which the design was chosen. This paper presents a graphical method for examining design robustness related to the SPV values using fraction of design space (FDS) plots by comparing designs across a number of potential models in a prespecified model space. The FDS plots show the various distributions of the SPV throughout the design space for different models for a chosen design on the same graph. The methods are demonstrated on several examples for different models and on a variety of design spaces.",
keywords = "Alphabetical Optimality Criteria, FDS Plot, Mixture Experiments, Model Reduction, Response Surface Designs, Scaled Prediction Variance",
author = "Ayca Ozol-Godfrey and Anderson-Cook, {Christine M.} and Douglas Montgomery",
year = "2005",
month = "7",
language = "English (US)",
volume = "37",
pages = "223--235",
journal = "Journal of Quality Technology",
issn = "0022-4065",
publisher = "American Society for Quality",
number = "3",

}

TY - JOUR

T1 - Fraction of design space plots for examining model robustness

AU - Ozol-Godfrey, Ayca

AU - Anderson-Cook, Christine M.

AU - Montgomery, Douglas

PY - 2005/7

Y1 - 2005/7

N2 - When choosing between competing designs, it is typical to specify a design space and model on which to base the comparison. The prediction capabilities of the design, specifically G- and V-efficiency using scaled prediction variance (SPV), are based on this chosen model. After the data are collected and individual effects are tested, some terms may not be significant in the model. In this case, the experimenter likely will decide to use a reduced model, which has only a portion of the terms included that were in the original model for which the design was chosen. This paper presents a graphical method for examining design robustness related to the SPV values using fraction of design space (FDS) plots by comparing designs across a number of potential models in a prespecified model space. The FDS plots show the various distributions of the SPV throughout the design space for different models for a chosen design on the same graph. The methods are demonstrated on several examples for different models and on a variety of design spaces.

AB - When choosing between competing designs, it is typical to specify a design space and model on which to base the comparison. The prediction capabilities of the design, specifically G- and V-efficiency using scaled prediction variance (SPV), are based on this chosen model. After the data are collected and individual effects are tested, some terms may not be significant in the model. In this case, the experimenter likely will decide to use a reduced model, which has only a portion of the terms included that were in the original model for which the design was chosen. This paper presents a graphical method for examining design robustness related to the SPV values using fraction of design space (FDS) plots by comparing designs across a number of potential models in a prespecified model space. The FDS plots show the various distributions of the SPV throughout the design space for different models for a chosen design on the same graph. The methods are demonstrated on several examples for different models and on a variety of design spaces.

KW - Alphabetical Optimality Criteria

KW - FDS Plot

KW - Mixture Experiments

KW - Model Reduction

KW - Response Surface Designs

KW - Scaled Prediction Variance

UR - http://www.scopus.com/inward/record.url?scp=22544471551&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22544471551&partnerID=8YFLogxK

M3 - Article

VL - 37

SP - 223

EP - 235

JO - Journal of Quality Technology

JF - Journal of Quality Technology

SN - 0022-4065

IS - 3

ER -