Optimal selection and ordering of columns in supersaturated designs

N. Niki, M. Iwata, H. Hashiguchi, Shu Yamada

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Two methods to select columns for assigning factors to work on supersaturated designs are proposed. The focus of interest is the degree of non-orthogonality between the selected columns. One method is the exhaustive enumeration of selections of p columns from all k columns to find the exact optimality, while the other is intended to find an approximate solution by applying techniques used in the corresponding analysis, aiming for ease of use as well as a reduction in the large computing time required for large k with the first method. Numerical illustrations for several typical design matrices reveal that the resulting "approximately" optimal assignments of factors to their columns are exactly optimal for any p. Ordering the columns in E(s2)-optimal designs results in promising new findings including a large number of E(s2)-optimal designs.

Original languageEnglish
Pages (from-to)2449-2462
Number of pages14
JournalJournal of Statistical Planning and Inference
Volume141
Issue number7
DOIs
Publication statusPublished - 2011 Jul
Externally publishedYes

Fingerprint

Supersaturated Design
Enumeration
Optimal design
Optimality
Approximate Solution
Assignment
Factors
Computing

Keywords

  • Corresponding analysis
  • Exhaustive enumeration
  • Factor assignment
  • Non-orthogonality
  • Optimal design

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Applied Mathematics
  • Statistics and Probability

Cite this

Optimal selection and ordering of columns in supersaturated designs. / Niki, N.; Iwata, M.; Hashiguchi, H.; Yamada, Shu.

In: Journal of Statistical Planning and Inference, Vol. 141, No. 7, 07.2011, p. 2449-2462.

Research output: Contribution to journalArticle

Niki, N. ; Iwata, M. ; Hashiguchi, H. ; Yamada, Shu. / Optimal selection and ordering of columns in supersaturated designs. In: Journal of Statistical Planning and Inference. 2011 ; Vol. 141, No. 7. pp. 2449-2462.
@article{7b4c2ceb93f74c1ba0eb130a60cf2f03,
title = "Optimal selection and ordering of columns in supersaturated designs",
abstract = "Two methods to select columns for assigning factors to work on supersaturated designs are proposed. The focus of interest is the degree of non-orthogonality between the selected columns. One method is the exhaustive enumeration of selections of p columns from all k columns to find the exact optimality, while the other is intended to find an approximate solution by applying techniques used in the corresponding analysis, aiming for ease of use as well as a reduction in the large computing time required for large k with the first method. Numerical illustrations for several typical design matrices reveal that the resulting {"}approximately{"} optimal assignments of factors to their columns are exactly optimal for any p. Ordering the columns in E(s2)-optimal designs results in promising new findings including a large number of E(s2)-optimal designs.",
keywords = "Corresponding analysis, Exhaustive enumeration, Factor assignment, Non-orthogonality, Optimal design",
author = "N. Niki and M. Iwata and H. Hashiguchi and Shu Yamada",
year = "2011",
month = "7",
doi = "10.1016/j.jspi.2011.02.007",
language = "English",
volume = "141",
pages = "2449--2462",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "7",

}

TY - JOUR

T1 - Optimal selection and ordering of columns in supersaturated designs

AU - Niki, N.

AU - Iwata, M.

AU - Hashiguchi, H.

AU - Yamada, Shu

PY - 2011/7

Y1 - 2011/7

N2 - Two methods to select columns for assigning factors to work on supersaturated designs are proposed. The focus of interest is the degree of non-orthogonality between the selected columns. One method is the exhaustive enumeration of selections of p columns from all k columns to find the exact optimality, while the other is intended to find an approximate solution by applying techniques used in the corresponding analysis, aiming for ease of use as well as a reduction in the large computing time required for large k with the first method. Numerical illustrations for several typical design matrices reveal that the resulting "approximately" optimal assignments of factors to their columns are exactly optimal for any p. Ordering the columns in E(s2)-optimal designs results in promising new findings including a large number of E(s2)-optimal designs.

AB - Two methods to select columns for assigning factors to work on supersaturated designs are proposed. The focus of interest is the degree of non-orthogonality between the selected columns. One method is the exhaustive enumeration of selections of p columns from all k columns to find the exact optimality, while the other is intended to find an approximate solution by applying techniques used in the corresponding analysis, aiming for ease of use as well as a reduction in the large computing time required for large k with the first method. Numerical illustrations for several typical design matrices reveal that the resulting "approximately" optimal assignments of factors to their columns are exactly optimal for any p. Ordering the columns in E(s2)-optimal designs results in promising new findings including a large number of E(s2)-optimal designs.

KW - Corresponding analysis

KW - Exhaustive enumeration

KW - Factor assignment

KW - Non-orthogonality

KW - Optimal design

UR - http://www.scopus.com/inward/record.url?scp=79952251316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952251316&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2011.02.007

DO - 10.1016/j.jspi.2011.02.007

M3 - Article

VL - 141

SP - 2449

EP - 2462

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 7

ER -