Three-level supersaturated designs

Shu Yamada, Dennis K J Lin

Research output: Contribution to journalArticle

73 Citations (Scopus)

Abstract

When experimentation is expensive and the number of factors is large, supersaturated designs can be helpful. They are essentially fractional factorial designs in which the number of factors is greater than the number of experimental runs. Previous studies have focused on two-level supersaturated designs. This paper presents a new class of three-level supersaturated designs with an equal occurrence property. It is shown that designs generated by such a universal construction method result in a low dependency among all columns.

Original languageEnglish
Pages (from-to)31-39
Number of pages9
JournalStatistics and Probability Letters
Volume45
Issue number1
Publication statusPublished - 1999 Oct 15
Externally publishedYes

Fingerprint

Supersaturated Design
Fractional Factorial Design
Experimentation
Factors

Keywords

  • χ statistic
  • Dependency
  • Factorial design
  • Inner product
  • Two-level design

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Statistics and Probability

Cite this

Three-level supersaturated designs. / Yamada, Shu; Lin, Dennis K J.

In: Statistics and Probability Letters, Vol. 45, No. 1, 15.10.1999, p. 31-39.

Research output: Contribution to journalArticle

Yamada, Shu ; Lin, Dennis K J. / Three-level supersaturated designs. In: Statistics and Probability Letters. 1999 ; Vol. 45, No. 1. pp. 31-39.
@article{20e75711aadc4fd4a6b10ffe328a99aa,
title = "Three-level supersaturated designs",
abstract = "When experimentation is expensive and the number of factors is large, supersaturated designs can be helpful. They are essentially fractional factorial designs in which the number of factors is greater than the number of experimental runs. Previous studies have focused on two-level supersaturated designs. This paper presents a new class of three-level supersaturated designs with an equal occurrence property. It is shown that designs generated by such a universal construction method result in a low dependency among all columns.",
keywords = "χ statistic, Dependency, Factorial design, Inner product, Two-level design",
author = "Shu Yamada and Lin, {Dennis K J}",
year = "1999",
month = "10",
day = "15",
language = "English",
volume = "45",
pages = "31--39",
journal = "Statistics and Probability Letters",
issn = "0167-7152",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Three-level supersaturated designs

AU - Yamada, Shu

AU - Lin, Dennis K J

PY - 1999/10/15

Y1 - 1999/10/15

N2 - When experimentation is expensive and the number of factors is large, supersaturated designs can be helpful. They are essentially fractional factorial designs in which the number of factors is greater than the number of experimental runs. Previous studies have focused on two-level supersaturated designs. This paper presents a new class of three-level supersaturated designs with an equal occurrence property. It is shown that designs generated by such a universal construction method result in a low dependency among all columns.

AB - When experimentation is expensive and the number of factors is large, supersaturated designs can be helpful. They are essentially fractional factorial designs in which the number of factors is greater than the number of experimental runs. Previous studies have focused on two-level supersaturated designs. This paper presents a new class of three-level supersaturated designs with an equal occurrence property. It is shown that designs generated by such a universal construction method result in a low dependency among all columns.

KW - χ statistic

KW - Dependency

KW - Factorial design

KW - Inner product

KW - Two-level design

UR - http://www.scopus.com/inward/record.url?scp=0002172932&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0002172932&partnerID=8YFLogxK

M3 - Article

VL - 45

SP - 31

EP - 39

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

SN - 0167-7152

IS - 1

ER -