Small screening design when the overall variance is unknown

Jiayu Peng, Dennis K.J. Lin

Research output: Contribution to journalArticle

Abstract

Consider the problem of a design for estimating all main effects and the overall error variance. The conventional choice is a saturated orthogonal array supplemented by several center points (as popularized in Response Surface Methodology). We propose an alternative design — the projection of a larger Hadamard matrix. In this article, we prove that the proposed design is optimal for estimating error variance, and thus is preferable over the conventional choice. Under various common error distributions, theoretical values of Var(σˆ2) are evaluated to illustrate our theory. Simulation results are provided to demonstrate that the proposed design achieves a more reliable estimate of error variance, as well as a reliable significant test. Furthermore, we study the optimal follow-up plan. Relevant optimality theories are established and a convenient construction method for optimal follow-up design is proposed.

Original languageEnglish (US)
Pages (from-to)1-9
Number of pages9
JournalJournal of Statistical Planning and Inference
Volume205
DOIs
StatePublished - Mar 1 2020

Fingerprint

Screening Design
Screening
Unknown
Hadamard matrices
Response Surface Methodology
Orthogonal Array
Hadamard Matrix
Main Effect
Optimality
Design
Projection
Alternatives
Estimate
Demonstrate
Simulation

All Science Journal Classification (ASJC) codes

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

Cite this

@article{0c48b5c0c5db459a9a86d17532021d2e,
title = "Small screening design when the overall variance is unknown",
abstract = "Consider the problem of a design for estimating all main effects and the overall error variance. The conventional choice is a saturated orthogonal array supplemented by several center points (as popularized in Response Surface Methodology). We propose an alternative design — the projection of a larger Hadamard matrix. In this article, we prove that the proposed design is optimal for estimating error variance, and thus is preferable over the conventional choice. Under various common error distributions, theoretical values of Var(σˆ2) are evaluated to illustrate our theory. Simulation results are provided to demonstrate that the proposed design achieves a more reliable estimate of error variance, as well as a reliable significant test. Furthermore, we study the optimal follow-up plan. Relevant optimality theories are established and a convenient construction method for optimal follow-up design is proposed.",
author = "Jiayu Peng and Lin, {Dennis K.J.}",
year = "2020",
month = "3",
day = "1",
doi = "10.1016/j.jspi.2019.04.011",
language = "English (US)",
volume = "205",
pages = "1--9",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",

}

Small screening design when the overall variance is unknown. / Peng, Jiayu; Lin, Dennis K.J.

In: Journal of Statistical Planning and Inference, Vol. 205, 01.03.2020, p. 1-9.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Small screening design when the overall variance is unknown

AU - Peng, Jiayu

AU - Lin, Dennis K.J.

PY - 2020/3/1

Y1 - 2020/3/1

N2 - Consider the problem of a design for estimating all main effects and the overall error variance. The conventional choice is a saturated orthogonal array supplemented by several center points (as popularized in Response Surface Methodology). We propose an alternative design — the projection of a larger Hadamard matrix. In this article, we prove that the proposed design is optimal for estimating error variance, and thus is preferable over the conventional choice. Under various common error distributions, theoretical values of Var(σˆ2) are evaluated to illustrate our theory. Simulation results are provided to demonstrate that the proposed design achieves a more reliable estimate of error variance, as well as a reliable significant test. Furthermore, we study the optimal follow-up plan. Relevant optimality theories are established and a convenient construction method for optimal follow-up design is proposed.

AB - Consider the problem of a design for estimating all main effects and the overall error variance. The conventional choice is a saturated orthogonal array supplemented by several center points (as popularized in Response Surface Methodology). We propose an alternative design — the projection of a larger Hadamard matrix. In this article, we prove that the proposed design is optimal for estimating error variance, and thus is preferable over the conventional choice. Under various common error distributions, theoretical values of Var(σˆ2) are evaluated to illustrate our theory. Simulation results are provided to demonstrate that the proposed design achieves a more reliable estimate of error variance, as well as a reliable significant test. Furthermore, we study the optimal follow-up plan. Relevant optimality theories are established and a convenient construction method for optimal follow-up design is proposed.

UR - http://www.scopus.com/inward/record.url?scp=85067892871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067892871&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2019.04.011

DO - 10.1016/j.jspi.2019.04.011

M3 - Article

AN - SCOPUS:85067892871

VL - 205

SP - 1

EP - 9

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

ER -