Full Screening Another View at One-Factor-at-a-Time Designs

B.W.M. Bettonvil

Research output: Working paperDiscussion paperOther research output

214 Downloads (Pure)

Abstract

Textbooks on Design Of Experiments invariably start by explaining why one-factor-at-a -time (OAT) is an inferior method. Here we will show that in a model with all interactions a variant of OAT is extremely efficient, provided that we only have non-negative parameters and that there are only a few large parameters. In the extreme, this means that there is one positive parameter. In that case, for m variables, that is, for 2m-1 parameters, the procedure only needs m+2 observations to find. In other examined cases, the proposed method is also very fast.
Original languageEnglish
Place of PublicationTilburg
PublisherInformation Management
Number of pages14
Volume2010-139
Publication statusPublished - 2010

Publication series

NameCentER Discussion Paper
Volume2010-139

Fingerprint

Textbooks
Design of experiments
Screening

Keywords

  • simulation
  • design of experiments
  • optimization
  • screening

Cite this

Bettonvil, B. W. M. (2010). Full Screening Another View at One-Factor-at-a-Time Designs. (CentER Discussion Paper; Vol. 2010-139). Tilburg: Information Management.
Bettonvil, B.W.M. / Full Screening Another View at One-Factor-at-a-Time Designs. Tilburg : Information Management, 2010. (CentER Discussion Paper).
@techreport{f9d6c1bee9e244f7978cdc65163d6123,
title = "Full Screening Another View at One-Factor-at-a-Time Designs",
abstract = "Textbooks on Design Of Experiments invariably start by explaining why one-factor-at-a -time (OAT) is an inferior method. Here we will show that in a model with all interactions a variant of OAT is extremely efficient, provided that we only have non-negative parameters and that there are only a few large parameters. In the extreme, this means that there is one positive parameter. In that case, for m variables, that is, for 2m-1 parameters, the procedure only needs m+2 observations to find. In other examined cases, the proposed method is also very fast.",
keywords = "simulation, design of experiments, optimization, screening",
author = "B.W.M. Bettonvil",
note = "Pagination: 14",
year = "2010",
language = "English",
volume = "2010-139",
series = "CentER Discussion Paper",
publisher = "Information Management",
type = "WorkingPaper",
institution = "Information Management",

}

Bettonvil, BWM 2010 'Full Screening Another View at One-Factor-at-a-Time Designs' CentER Discussion Paper, vol. 2010-139, Information Management, Tilburg.

Full Screening Another View at One-Factor-at-a-Time Designs. / Bettonvil, B.W.M.

Tilburg : Information Management, 2010. (CentER Discussion Paper; Vol. 2010-139).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Full Screening Another View at One-Factor-at-a-Time Designs

AU - Bettonvil, B.W.M.

N1 - Pagination: 14

PY - 2010

Y1 - 2010

N2 - Textbooks on Design Of Experiments invariably start by explaining why one-factor-at-a -time (OAT) is an inferior method. Here we will show that in a model with all interactions a variant of OAT is extremely efficient, provided that we only have non-negative parameters and that there are only a few large parameters. In the extreme, this means that there is one positive parameter. In that case, for m variables, that is, for 2m-1 parameters, the procedure only needs m+2 observations to find. In other examined cases, the proposed method is also very fast.

AB - Textbooks on Design Of Experiments invariably start by explaining why one-factor-at-a -time (OAT) is an inferior method. Here we will show that in a model with all interactions a variant of OAT is extremely efficient, provided that we only have non-negative parameters and that there are only a few large parameters. In the extreme, this means that there is one positive parameter. In that case, for m variables, that is, for 2m-1 parameters, the procedure only needs m+2 observations to find. In other examined cases, the proposed method is also very fast.

KW - simulation

KW - design of experiments

KW - optimization

KW - screening

M3 - Discussion paper

VL - 2010-139

T3 - CentER Discussion Paper

BT - Full Screening Another View at One-Factor-at-a-Time Designs

PB - Information Management

CY - Tilburg

ER -

Bettonvil BWM. Full Screening Another View at One-Factor-at-a-Time Designs. Tilburg: Information Management. 2010. (CentER Discussion Paper).