Three-level main-effects designs exploiting prior information about model uncertainty

Pi Wen Tsai, Steven G. Gilmour, Roger Mead

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

To explore the projection efficiency of a design, Tsai, et al [2000. Projective three-level main effects designs robust to model uncertainty. Biometrika 87, 467-475] introduced the Q criterion to compare three-level main-effects designs for quantitative factors that allow the consideration of interactions in addition to main effects. In this paper, we extend their method and focus on the case in which experimenters have some prior knowledge, in advance of running the experiment, about the probabilities of effects being non-negligible. A criterion which incorporates experimenters' prior beliefs about the importance of each effect is introduced to compare orthogonal, or nearly orthogonal, main effects designs with robustness to interactions as a secondary consideration. We show that this criterion, exploiting prior information about model uncertainty, can lead to more appropriate designs reflecting experimenters' prior beliefs.

Original languageEnglish
Pages (from-to)619-627
Number of pages9
JournalJournal of Statistical Planning and Inference
Volume137
Issue number2
DOIs
Publication statusPublished - 2007 Feb 1

Fingerprint

Main Effect
Model Uncertainty
Prior Information
Robust Design
Prior Knowledge
Interaction
Projection
Robustness
Design
Model uncertainty
Prior information
Information model
Uncertainty
Experiment
Experiments
Beliefs

Keywords

  • Bayesian optimal designs
  • Factor screening
  • Orthogonal array
  • Prior information
  • Projection

ASJC Scopus subject areas

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

Cite this

Three-level main-effects designs exploiting prior information about model uncertainty. / Tsai, Pi Wen; Gilmour, Steven G.; Mead, Roger.

In: Journal of Statistical Planning and Inference, Vol. 137, No. 2, 01.02.2007, p. 619-627.

Research output: Contribution to journalArticle

@article{b4a93c858f51480ea8c5a824cc9e833d,
title = "Three-level main-effects designs exploiting prior information about model uncertainty",
abstract = "To explore the projection efficiency of a design, Tsai, et al [2000. Projective three-level main effects designs robust to model uncertainty. Biometrika 87, 467-475] introduced the Q criterion to compare three-level main-effects designs for quantitative factors that allow the consideration of interactions in addition to main effects. In this paper, we extend their method and focus on the case in which experimenters have some prior knowledge, in advance of running the experiment, about the probabilities of effects being non-negligible. A criterion which incorporates experimenters' prior beliefs about the importance of each effect is introduced to compare orthogonal, or nearly orthogonal, main effects designs with robustness to interactions as a secondary consideration. We show that this criterion, exploiting prior information about model uncertainty, can lead to more appropriate designs reflecting experimenters' prior beliefs.",
keywords = "Bayesian optimal designs, Factor screening, Orthogonal array, Prior information, Projection",
author = "Tsai, {Pi Wen} and Gilmour, {Steven G.} and Roger Mead",
year = "2007",
month = "2",
day = "1",
doi = "10.1016/j.jspi.2006.01.003",
language = "English",
volume = "137",
pages = "619--627",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Three-level main-effects designs exploiting prior information about model uncertainty

AU - Tsai, Pi Wen

AU - Gilmour, Steven G.

AU - Mead, Roger

PY - 2007/2/1

Y1 - 2007/2/1

N2 - To explore the projection efficiency of a design, Tsai, et al [2000. Projective three-level main effects designs robust to model uncertainty. Biometrika 87, 467-475] introduced the Q criterion to compare three-level main-effects designs for quantitative factors that allow the consideration of interactions in addition to main effects. In this paper, we extend their method and focus on the case in which experimenters have some prior knowledge, in advance of running the experiment, about the probabilities of effects being non-negligible. A criterion which incorporates experimenters' prior beliefs about the importance of each effect is introduced to compare orthogonal, or nearly orthogonal, main effects designs with robustness to interactions as a secondary consideration. We show that this criterion, exploiting prior information about model uncertainty, can lead to more appropriate designs reflecting experimenters' prior beliefs.

AB - To explore the projection efficiency of a design, Tsai, et al [2000. Projective three-level main effects designs robust to model uncertainty. Biometrika 87, 467-475] introduced the Q criterion to compare three-level main-effects designs for quantitative factors that allow the consideration of interactions in addition to main effects. In this paper, we extend their method and focus on the case in which experimenters have some prior knowledge, in advance of running the experiment, about the probabilities of effects being non-negligible. A criterion which incorporates experimenters' prior beliefs about the importance of each effect is introduced to compare orthogonal, or nearly orthogonal, main effects designs with robustness to interactions as a secondary consideration. We show that this criterion, exploiting prior information about model uncertainty, can lead to more appropriate designs reflecting experimenters' prior beliefs.

KW - Bayesian optimal designs

KW - Factor screening

KW - Orthogonal array

KW - Prior information

KW - Projection

UR - http://www.scopus.com/inward/record.url?scp=33749487248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749487248&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2006.01.003

DO - 10.1016/j.jspi.2006.01.003

M3 - Article

AN - SCOPUS:33749487248

VL - 137

SP - 619

EP - 627

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 2

ER -