A general method of constructing E(s2)-optimal supersaturated designs

Neil A. Butler; Roger Mead; Kent M. Eskridge; Steven G. Gilmour

A general method of constructing E(s²)-optimal supersaturated designs

Neil A. Butler^*, Roger Mead, Kent M. Eskridge, Steven G. Gilmour

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

81 Citations (Scopus)

Abstract

There has been much recent interest in supersaturated designs and their application in factor screening experiments. Supersaturated designs have mainly been constructed by using the E(s²)-optimality criterion originally proposed by Booth and Cox in 1962. However, until now E(s²)-optimal designs have only been established with certainty for n experimental runs when the number of factors m is a multiple of n - 1, and in adjacent cases where m = q(n - 1) + r (\r\ ≤ 2, q an integer). A method of constructing E(s²)-optimal designs is presented which allows a reasonably complete solution to be found for various numbers of runs n including n = 8, 12, 16, 20, 24, 32, 40, 48, 64.

Original language	English
Pages (from-to)	621-632
Number of pages	12
Journal	Journal of the Royal Statistical Society. Series B: Statistical Methodology
Volume	63
Issue number	3
Publication status	Published - 2001

Keywords

Balanced incomplete-block designs
Cyclic generators
Effect sparsity
Hadamard matrices
Lower bound
Orthogonality
Plackett-Burman designs
Screening designs

Cite this

@article{5067b545fe0a47bf89fae0d797b7ec24,

title = "A general method of constructing E(s2)-optimal supersaturated designs",

abstract = "There has been much recent interest in supersaturated designs and their application in factor screening experiments. Supersaturated designs have mainly been constructed by using the E(s2)-optimality criterion originally proposed by Booth and Cox in 1962. However, until now E(s2)-optimal designs have only been established with certainty for n experimental runs when the number of factors m is a multiple of n - 1, and in adjacent cases where m = q(n - 1) + r (\r\ ≤ 2, q an integer). A method of constructing E(s2)-optimal designs is presented which allows a reasonably complete solution to be found for various numbers of runs n including n = 8, 12, 16, 20, 24, 32, 40, 48, 64.",

keywords = "Balanced incomplete-block designs, Cyclic generators, Effect sparsity, Hadamard matrices, Lower bound, Orthogonality, Plackett-Burman designs, Screening designs",

author = "Butler, {Neil A.} and Roger Mead and Eskridge, {Kent M.} and Gilmour, {Steven G.}",

year = "2001",

language = "English",

volume = "63",

pages = "621--632",

journal = "Journal of the Royal Statistical Society. Series B: Statistical Methodology",

issn = "1369-7412",

publisher = "Wiley-Blackwell",

number = "3",

}

TY - JOUR

T1 - A general method of constructing E(s2)-optimal supersaturated designs

AU - Butler, Neil A.

AU - Mead, Roger

AU - Eskridge, Kent M.

AU - Gilmour, Steven G.

PY - 2001

Y1 - 2001

N2 - There has been much recent interest in supersaturated designs and their application in factor screening experiments. Supersaturated designs have mainly been constructed by using the E(s2)-optimality criterion originally proposed by Booth and Cox in 1962. However, until now E(s2)-optimal designs have only been established with certainty for n experimental runs when the number of factors m is a multiple of n - 1, and in adjacent cases where m = q(n - 1) + r (\r\ ≤ 2, q an integer). A method of constructing E(s2)-optimal designs is presented which allows a reasonably complete solution to be found for various numbers of runs n including n = 8, 12, 16, 20, 24, 32, 40, 48, 64.

AB - There has been much recent interest in supersaturated designs and their application in factor screening experiments. Supersaturated designs have mainly been constructed by using the E(s2)-optimality criterion originally proposed by Booth and Cox in 1962. However, until now E(s2)-optimal designs have only been established with certainty for n experimental runs when the number of factors m is a multiple of n - 1, and in adjacent cases where m = q(n - 1) + r (\r\ ≤ 2, q an integer). A method of constructing E(s2)-optimal designs is presented which allows a reasonably complete solution to be found for various numbers of runs n including n = 8, 12, 16, 20, 24, 32, 40, 48, 64.

KW - Balanced incomplete-block designs

KW - Cyclic generators

KW - Effect sparsity

KW - Hadamard matrices

KW - Lower bound

KW - Orthogonality

KW - Plackett-Burman designs

KW - Screening designs

UR - http://www.scopus.com/inward/record.url?scp=0035649942&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0035649942

SN - 1369-7412

VL - 63

SP - 621

EP - 632

JO - Journal of the Royal Statistical Society. Series B: Statistical Methodology

JF - Journal of the Royal Statistical Society. Series B: Statistical Methodology

IS - 3

ER -

A general method of constructing E(s²)-optimal supersaturated designs

Abstract

Keywords

Other files and links

Fingerprint

Cite this