A general construction method for mixed-level supersaturated design

Shu Yamada, Michiyo Matsui, Tomomi Matsui, Dennis K J Lin, Takenori Takahashi

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

When the number of the experimental variables is large, the first and most critical step is to identify the (few) active factors among those (many) candidate factors. Supersaturated design is shown to be helpful for such a critical first step. A general construction method for mixed-level supersaturated design is proposed. The newly constructed design has several advantages, including the flexibility for the number of runs and the assurance of upper bound of the (pairwise) dependency among all design columns. Specific applications to the construction of two-level and three-level mixed-level designs are discussed in detail.

Original languageEnglish
Pages (from-to)254-265
Number of pages12
JournalComputational Statistics and Data Analysis
Volume50
Issue number1 SPEC. ISS.
DOIs
Publication statusPublished - 2006 Jan 10
Externally publishedYes

Fingerprint

Supersaturated Design
Pairwise
Flexibility
Upper bound
Design

Keywords

  • χ value
  • Algorithmic approach
  • Non-orthogonality

ASJC Scopus subject areas

  • Statistics and Probability
  • Computational Theory and Mathematics
  • Computational Mathematics
  • Applied Mathematics

Cite this

A general construction method for mixed-level supersaturated design. / Yamada, Shu; Matsui, Michiyo; Matsui, Tomomi; Lin, Dennis K J; Takahashi, Takenori.

In: Computational Statistics and Data Analysis, Vol. 50, No. 1 SPEC. ISS., 10.01.2006, p. 254-265.

Research output: Contribution to journalArticle

Yamada, Shu ; Matsui, Michiyo ; Matsui, Tomomi ; Lin, Dennis K J ; Takahashi, Takenori. / A general construction method for mixed-level supersaturated design. In: Computational Statistics and Data Analysis. 2006 ; Vol. 50, No. 1 SPEC. ISS. pp. 254-265.
@article{66629b276b854afab29b005152c17d5b,
title = "A general construction method for mixed-level supersaturated design",
abstract = "When the number of the experimental variables is large, the first and most critical step is to identify the (few) active factors among those (many) candidate factors. Supersaturated design is shown to be helpful for such a critical first step. A general construction method for mixed-level supersaturated design is proposed. The newly constructed design has several advantages, including the flexibility for the number of runs and the assurance of upper bound of the (pairwise) dependency among all design columns. Specific applications to the construction of two-level and three-level mixed-level designs are discussed in detail.",
keywords = "χ value, Algorithmic approach, Non-orthogonality",
author = "Shu Yamada and Michiyo Matsui and Tomomi Matsui and Lin, {Dennis K J} and Takenori Takahashi",
year = "2006",
month = "1",
day = "10",
doi = "10.1016/j.csda.2004.07.018",
language = "English",
volume = "50",
pages = "254--265",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",
number = "1 SPEC. ISS.",

}

TY - JOUR

T1 - A general construction method for mixed-level supersaturated design

AU - Yamada, Shu

AU - Matsui, Michiyo

AU - Matsui, Tomomi

AU - Lin, Dennis K J

AU - Takahashi, Takenori

PY - 2006/1/10

Y1 - 2006/1/10

N2 - When the number of the experimental variables is large, the first and most critical step is to identify the (few) active factors among those (many) candidate factors. Supersaturated design is shown to be helpful for such a critical first step. A general construction method for mixed-level supersaturated design is proposed. The newly constructed design has several advantages, including the flexibility for the number of runs and the assurance of upper bound of the (pairwise) dependency among all design columns. Specific applications to the construction of two-level and three-level mixed-level designs are discussed in detail.

AB - When the number of the experimental variables is large, the first and most critical step is to identify the (few) active factors among those (many) candidate factors. Supersaturated design is shown to be helpful for such a critical first step. A general construction method for mixed-level supersaturated design is proposed. The newly constructed design has several advantages, including the flexibility for the number of runs and the assurance of upper bound of the (pairwise) dependency among all design columns. Specific applications to the construction of two-level and three-level mixed-level designs are discussed in detail.

KW - χ value

KW - Algorithmic approach

KW - Non-orthogonality

UR - http://www.scopus.com/inward/record.url?scp=24644515869&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24644515869&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2004.07.018

DO - 10.1016/j.csda.2004.07.018

M3 - Article

AN - SCOPUS:24644515869

VL - 50

SP - 254

EP - 265

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 1 SPEC. ISS.

ER -