Analysis of supersaturated designs

Don R. Holcomb, Douglas Montgomery, W. Matthew Carlyle

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

Supersaturated designs offer a potentially useful way to investigate many factors with very few experimental runs. These designs are used to investigate m factors with n experimental runs, where m > n - 1. We evaluate several methods for analyzing a broad range of supersaturated designs and provide a basic explanation of these procedures. We show that the contrasts of a supersaturated design follow a permuted multivariate hypergeometric distribution, which may be approximated with a normal distribution. The analysis methods presented are based on methods for unreplicated fractional factorial designs. Two contrast-based analysis methods are presented, and the assumptions of the underlying model are described for a wide range of supersaturated designs.

Original languageEnglish (US)
Pages (from-to)13-27
Number of pages15
JournalJournal of Quality Technology
Volume35
Issue number1
StatePublished - Jan 2003

Fingerprint

Supersaturated Design
Hypergeometric Distribution
Fractional Factorial Design
Multivariate Distribution
Range of data
Gaussian distribution
Normal distribution
Evaluate

Keywords

  • Contrasts
  • Factorial designs
  • Screening

ASJC Scopus subject areas

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

Cite this

Holcomb, D. R., Montgomery, D., & Carlyle, W. M. (2003). Analysis of supersaturated designs. Journal of Quality Technology, 35(1), 13-27.

Analysis of supersaturated designs. / Holcomb, Don R.; Montgomery, Douglas; Carlyle, W. Matthew.

In: Journal of Quality Technology, Vol. 35, No. 1, 01.2003, p. 13-27.

Research output: Contribution to journalArticle

Holcomb, DR, Montgomery, D & Carlyle, WM 2003, 'Analysis of supersaturated designs', Journal of Quality Technology, vol. 35, no. 1, pp. 13-27.
Holcomb, Don R. ; Montgomery, Douglas ; Carlyle, W. Matthew. / Analysis of supersaturated designs. In: Journal of Quality Technology. 2003 ; Vol. 35, No. 1. pp. 13-27.
@article{1cd9f5de058c4babbda255ef5c0156bf,
title = "Analysis of supersaturated designs",
abstract = "Supersaturated designs offer a potentially useful way to investigate many factors with very few experimental runs. These designs are used to investigate m factors with n experimental runs, where m > n - 1. We evaluate several methods for analyzing a broad range of supersaturated designs and provide a basic explanation of these procedures. We show that the contrasts of a supersaturated design follow a permuted multivariate hypergeometric distribution, which may be approximated with a normal distribution. The analysis methods presented are based on methods for unreplicated fractional factorial designs. Two contrast-based analysis methods are presented, and the assumptions of the underlying model are described for a wide range of supersaturated designs.",
keywords = "Contrasts, Factorial designs, Screening",
author = "Holcomb, {Don R.} and Douglas Montgomery and Carlyle, {W. Matthew}",
year = "2003",
month = "1",
language = "English (US)",
volume = "35",
pages = "13--27",
journal = "Journal of Quality Technology",
issn = "0022-4065",
publisher = "American Society for Quality",
number = "1",

}

TY - JOUR

T1 - Analysis of supersaturated designs

AU - Holcomb, Don R.

AU - Montgomery, Douglas

AU - Carlyle, W. Matthew

PY - 2003/1

Y1 - 2003/1

N2 - Supersaturated designs offer a potentially useful way to investigate many factors with very few experimental runs. These designs are used to investigate m factors with n experimental runs, where m > n - 1. We evaluate several methods for analyzing a broad range of supersaturated designs and provide a basic explanation of these procedures. We show that the contrasts of a supersaturated design follow a permuted multivariate hypergeometric distribution, which may be approximated with a normal distribution. The analysis methods presented are based on methods for unreplicated fractional factorial designs. Two contrast-based analysis methods are presented, and the assumptions of the underlying model are described for a wide range of supersaturated designs.

AB - Supersaturated designs offer a potentially useful way to investigate many factors with very few experimental runs. These designs are used to investigate m factors with n experimental runs, where m > n - 1. We evaluate several methods for analyzing a broad range of supersaturated designs and provide a basic explanation of these procedures. We show that the contrasts of a supersaturated design follow a permuted multivariate hypergeometric distribution, which may be approximated with a normal distribution. The analysis methods presented are based on methods for unreplicated fractional factorial designs. Two contrast-based analysis methods are presented, and the assumptions of the underlying model are described for a wide range of supersaturated designs.

KW - Contrasts

KW - Factorial designs

KW - Screening

UR - http://www.scopus.com/inward/record.url?scp=1042292398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1042292398&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:1042292398

VL - 35

SP - 13

EP - 27

JO - Journal of Quality Technology

JF - Journal of Quality Technology

SN - 0022-4065

IS - 1

ER -