Mixture-process variable experiments with noise variables

Heidi B. Goldfarb, Connie M. Borror, Douglas Montgomery

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

In a mixture experiment, the design factors are mixture components whose proportions are varied, and the response variables are assumed to depend only on these component proportions. In addition to the mixture components, the experimenter may be interested in other variables that can be varied independently of one another and of the mixture components. We consider the case where one or more of these variables is a noise variable, or a variable that cannot be controlled in practice. We develop models for these robust mixture formulation problems. We then derive mean and variance functions and illustrate their use in formulation optimization. Cases of uncorrelated and correlated noise variables are addressed.

Original languageEnglish (US)
Pages (from-to)393-405
Number of pages13
JournalJournal of Quality Technology
Volume35
Issue number4
StatePublished - Oct 2003

Fingerprint

Experiment
Experiments
Proportion
Mixture Experiments
Correlated Noise
Variance Function
Formulation
Process variables
Optimization
Model
Design
Factors
Problem formulation

Keywords

  • Mixture experiments
  • Mixture-process experiments
  • Noise variables
  • Response surface methodology
  • Robust parameter design

ASJC Scopus subject areas

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

Cite this

Mixture-process variable experiments with noise variables. / Goldfarb, Heidi B.; Borror, Connie M.; Montgomery, Douglas.

In: Journal of Quality Technology, Vol. 35, No. 4, 10.2003, p. 393-405.

Research output: Contribution to journalArticle

Goldfarb, Heidi B. ; Borror, Connie M. ; Montgomery, Douglas. / Mixture-process variable experiments with noise variables. In: Journal of Quality Technology. 2003 ; Vol. 35, No. 4. pp. 393-405.
@article{fdad2b1b94c94ef9bde64f30cea92759,
title = "Mixture-process variable experiments with noise variables",
abstract = "In a mixture experiment, the design factors are mixture components whose proportions are varied, and the response variables are assumed to depend only on these component proportions. In addition to the mixture components, the experimenter may be interested in other variables that can be varied independently of one another and of the mixture components. We consider the case where one or more of these variables is a noise variable, or a variable that cannot be controlled in practice. We develop models for these robust mixture formulation problems. We then derive mean and variance functions and illustrate their use in formulation optimization. Cases of uncorrelated and correlated noise variables are addressed.",
keywords = "Mixture experiments, Mixture-process experiments, Noise variables, Response surface methodology, Robust parameter design",
author = "Goldfarb, {Heidi B.} and Borror, {Connie M.} and Douglas Montgomery",
year = "2003",
month = "10",
language = "English (US)",
volume = "35",
pages = "393--405",
journal = "Journal of Quality Technology",
issn = "0022-4065",
publisher = "American Society for Quality",
number = "4",

}

TY - JOUR

T1 - Mixture-process variable experiments with noise variables

AU - Goldfarb, Heidi B.

AU - Borror, Connie M.

AU - Montgomery, Douglas

PY - 2003/10

Y1 - 2003/10

N2 - In a mixture experiment, the design factors are mixture components whose proportions are varied, and the response variables are assumed to depend only on these component proportions. In addition to the mixture components, the experimenter may be interested in other variables that can be varied independently of one another and of the mixture components. We consider the case where one or more of these variables is a noise variable, or a variable that cannot be controlled in practice. We develop models for these robust mixture formulation problems. We then derive mean and variance functions and illustrate their use in formulation optimization. Cases of uncorrelated and correlated noise variables are addressed.

AB - In a mixture experiment, the design factors are mixture components whose proportions are varied, and the response variables are assumed to depend only on these component proportions. In addition to the mixture components, the experimenter may be interested in other variables that can be varied independently of one another and of the mixture components. We consider the case where one or more of these variables is a noise variable, or a variable that cannot be controlled in practice. We develop models for these robust mixture formulation problems. We then derive mean and variance functions and illustrate their use in formulation optimization. Cases of uncorrelated and correlated noise variables are addressed.

KW - Mixture experiments

KW - Mixture-process experiments

KW - Noise variables

KW - Response surface methodology

KW - Robust parameter design

UR - http://www.scopus.com/inward/record.url?scp=1042304012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1042304012&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1042304012

VL - 35

SP - 393

EP - 405

JO - Journal of Quality Technology

JF - Journal of Quality Technology

SN - 0022-4065

IS - 4

ER -