Selection of active factors by stepwise regression in the data analysis of supersaturated design

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Supersaturated design is a type of fractional factorial design in which the number of columns is greater than the number of rows. Several articles have considered methods for constructing supersaturated designs to assure a low level of nonorthogonality for all paired columns. Stepwise selection is recommended for the selection of active factors in data analysis for supersaturated design, under an assumption of the effect sparsity. This article considers selection errors of stepwise regression in the analysis of supersaturated designs. Specifically, type II error in the selection of stepwise regression is examined using simulation. Based on the results of simulation, some guidelines for data analysis of supersaturated design are discussed.

Original languageEnglish
Pages (from-to)501-513
Number of pages13
JournalQuality Engineering
Volume16
Issue number4
DOIs
Publication statusPublished - 2004 Jun
Externally publishedYes

Keywords

  • Active factors
  • Alias
  • Simulation study
  • Type I and II errors

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Selection of active factors by stepwise regression in the data analysis of supersaturated design. / Yamada, Shu.

In: Quality Engineering, Vol. 16, No. 4, 06.2004, p. 501-513.

Research output: Contribution to journalArticle

@article{8f0185b67451484fa9471f407f8291bd,
title = "Selection of active factors by stepwise regression in the data analysis of supersaturated design",
abstract = "Supersaturated design is a type of fractional factorial design in which the number of columns is greater than the number of rows. Several articles have considered methods for constructing supersaturated designs to assure a low level of nonorthogonality for all paired columns. Stepwise selection is recommended for the selection of active factors in data analysis for supersaturated design, under an assumption of the effect sparsity. This article considers selection errors of stepwise regression in the analysis of supersaturated designs. Specifically, type II error in the selection of stepwise regression is examined using simulation. Based on the results of simulation, some guidelines for data analysis of supersaturated design are discussed.",
keywords = "Active factors, Alias, Simulation study, Type I and II errors",
author = "Shu Yamada",
year = "2004",
month = "6",
doi = "10.1081/QEN-120038012",
language = "English",
volume = "16",
pages = "501--513",
journal = "Drug Development and Industrial Pharmacy",
issn = "0898-2112",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

TY - JOUR

T1 - Selection of active factors by stepwise regression in the data analysis of supersaturated design

AU - Yamada, Shu

PY - 2004/6

Y1 - 2004/6

N2 - Supersaturated design is a type of fractional factorial design in which the number of columns is greater than the number of rows. Several articles have considered methods for constructing supersaturated designs to assure a low level of nonorthogonality for all paired columns. Stepwise selection is recommended for the selection of active factors in data analysis for supersaturated design, under an assumption of the effect sparsity. This article considers selection errors of stepwise regression in the analysis of supersaturated designs. Specifically, type II error in the selection of stepwise regression is examined using simulation. Based on the results of simulation, some guidelines for data analysis of supersaturated design are discussed.

AB - Supersaturated design is a type of fractional factorial design in which the number of columns is greater than the number of rows. Several articles have considered methods for constructing supersaturated designs to assure a low level of nonorthogonality for all paired columns. Stepwise selection is recommended for the selection of active factors in data analysis for supersaturated design, under an assumption of the effect sparsity. This article considers selection errors of stepwise regression in the analysis of supersaturated designs. Specifically, type II error in the selection of stepwise regression is examined using simulation. Based on the results of simulation, some guidelines for data analysis of supersaturated design are discussed.

KW - Active factors

KW - Alias

KW - Simulation study

KW - Type I and II errors

UR - http://www.scopus.com/inward/record.url?scp=4344682883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4344682883&partnerID=8YFLogxK

U2 - 10.1081/QEN-120038012

DO - 10.1081/QEN-120038012

M3 - Article

AN - SCOPUS:4344682883

VL - 16

SP - 501

EP - 513

JO - Drug Development and Industrial Pharmacy

JF - Drug Development and Industrial Pharmacy

SN - 0898-2112

IS - 4

ER -