Construction of mixed-level supersaturated design

Shu Yamada, Deanis K J Lin

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

Supersaturated design is a form of fractional factorial design in which the number of columns is greater than the number of experimental runs. Construction methods of supersaturated design have been mainly focused on two levels cases. Much practical experience, however, indicates that two-level may sometimes be inadequate. This paper proposed a construction method of mixed-level supersaturated designs consisting of two-level and three-level columns. The Χ2 statistic is used for a measure of dependency of the design columns. The dependency properties for the newly constructed designs are derived and discussed. It is shown that these new designs have low dependencies and thus can be useful for practical uses.

Original languageEnglish
Pages (from-to)205-214
Number of pages10
JournalMetrika
Volume56
Issue number3
DOIs
Publication statusPublished - 2002
Externally publishedYes

Fingerprint

Supersaturated Design
Fractional Factorial Design
Statistic
Design

Keywords

  • Χ-statistics
  • Average and maximum dependency
  • Orthogonality

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Construction of mixed-level supersaturated design. / Yamada, Shu; Lin, Deanis K J.

In: Metrika, Vol. 56, No. 3, 2002, p. 205-214.

Research output: Contribution to journalArticle

Yamada, Shu ; Lin, Deanis K J. / Construction of mixed-level supersaturated design. In: Metrika. 2002 ; Vol. 56, No. 3. pp. 205-214.
@article{b8c46616622c4d9780ed4579ad032d64,
title = "Construction of mixed-level supersaturated design",
abstract = "Supersaturated design is a form of fractional factorial design in which the number of columns is greater than the number of experimental runs. Construction methods of supersaturated design have been mainly focused on two levels cases. Much practical experience, however, indicates that two-level may sometimes be inadequate. This paper proposed a construction method of mixed-level supersaturated designs consisting of two-level and three-level columns. The Χ2 statistic is used for a measure of dependency of the design columns. The dependency properties for the newly constructed designs are derived and discussed. It is shown that these new designs have low dependencies and thus can be useful for practical uses.",
keywords = "Χ-statistics, Average and maximum dependency, Orthogonality",
author = "Shu Yamada and Lin, {Deanis K J}",
year = "2002",
doi = "10.1007/s001840100173",
language = "English",
volume = "56",
pages = "205--214",
journal = "Metrika",
issn = "0026-1335",
publisher = "Springer Verlag",
number = "3",

}

TY - JOUR

T1 - Construction of mixed-level supersaturated design

AU - Yamada, Shu

AU - Lin, Deanis K J

PY - 2002

Y1 - 2002

N2 - Supersaturated design is a form of fractional factorial design in which the number of columns is greater than the number of experimental runs. Construction methods of supersaturated design have been mainly focused on two levels cases. Much practical experience, however, indicates that two-level may sometimes be inadequate. This paper proposed a construction method of mixed-level supersaturated designs consisting of two-level and three-level columns. The Χ2 statistic is used for a measure of dependency of the design columns. The dependency properties for the newly constructed designs are derived and discussed. It is shown that these new designs have low dependencies and thus can be useful for practical uses.

AB - Supersaturated design is a form of fractional factorial design in which the number of columns is greater than the number of experimental runs. Construction methods of supersaturated design have been mainly focused on two levels cases. Much practical experience, however, indicates that two-level may sometimes be inadequate. This paper proposed a construction method of mixed-level supersaturated designs consisting of two-level and three-level columns. The Χ2 statistic is used for a measure of dependency of the design columns. The dependency properties for the newly constructed designs are derived and discussed. It is shown that these new designs have low dependencies and thus can be useful for practical uses.

KW - Χ-statistics

KW - Average and maximum dependency

KW - Orthogonality

UR - http://www.scopus.com/inward/record.url?scp=0036459531&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036459531&partnerID=8YFLogxK

U2 - 10.1007/s001840100173

DO - 10.1007/s001840100173

M3 - Article

AN - SCOPUS:0036459531

VL - 56

SP - 205

EP - 214

JO - Metrika

JF - Metrika

SN - 0026-1335

IS - 3

ER -