Optimal cross-over designs for full interaction models

Rosemary Anne Bailey; Pierre Druilhet

doi:10.1214/14-AOS1247

Optimal cross-over designs for full interaction models

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

Abstract

We consider repeated measurement designs when a residual or carry-over effect may be present in at most one later period. Since assuming an additive model may be unrealistic for some applications and leads to biased estimation of treatment effects, we consider a model with interactions between carry-over and direct treatment effects. When the aim of the experiment is to study the effects of a treatment used alone, we obtain universally optimal approximate
designs. We also propose some efficient designs with a reduced number of subjects.

Original language	English
Pages (from-to)	2282-2300
Number of pages	19
Journal	Annals of Statistics
Volume	42
Issue number	6
Early online date	24 Oct 2014
DOIs	https://doi.org/10.1214/14-AOS1247
Publication status	Published - Dec 2014

Keywords

Cross-over designs
Repeated measurement designs
Interference models
Optimal design
Total effects

Access to Document

10.1214/14-AOS1247

1411.0862v1
© 2014. Institute of Mathematical Statistics.This is an electronic reprint of a work that was published in The Annals of Statistics DOI http://dx.doi.org/10.1214/14-AOS1247
Final published version, 224 KB

R. A. Bailey
- rab24st-andrews.acuk
- Statistics - Professor
- Centre for Interdisciplinary Research in Computational Algebra
Person: Academic

Cite this

@article{4d00649ac9b54ae3b47ec82744356d60,

title = "Optimal cross-over designs for full interaction models",

abstract = "We consider repeated measurement designs when a residual or carry-over effect may be present in at most one later period. Since assuming an additive model may be unrealistic for some applications and leads to biased estimation of treatment effects, we consider a model with interactions between carry-over and direct treatment effects. When the aim of the experiment is to study the effects of a treatment used alone, we obtain universally optimal approximate designs. We also propose some efficient designs with a reduced number of subjects.",

keywords = "Cross-over designs, Repeated measurement designs, Interference models, Optimal design, Total effects",

author = "Bailey, {Rosemary Anne} and Pierre Druilhet",

year = "2014",

month = dec,

doi = "10.1214/14-AOS1247",

language = "English",

volume = "42",

pages = "2282--2300",

journal = "Annals of Statistics",

issn = "0090-5364",

publisher = "Institute of Mathematical Statistics",

number = "6",

}

TY - JOUR

T1 - Optimal cross-over designs for full interaction models

AU - Bailey, Rosemary Anne

AU - Druilhet, Pierre

PY - 2014/12

Y1 - 2014/12

N2 - We consider repeated measurement designs when a residual or carry-over effect may be present in at most one later period. Since assuming an additive model may be unrealistic for some applications and leads to biased estimation of treatment effects, we consider a model with interactions between carry-over and direct treatment effects. When the aim of the experiment is to study the effects of a treatment used alone, we obtain universally optimal approximate designs. We also propose some efficient designs with a reduced number of subjects.

AB - We consider repeated measurement designs when a residual or carry-over effect may be present in at most one later period. Since assuming an additive model may be unrealistic for some applications and leads to biased estimation of treatment effects, we consider a model with interactions between carry-over and direct treatment effects. When the aim of the experiment is to study the effects of a treatment used alone, we obtain universally optimal approximate designs. We also propose some efficient designs with a reduced number of subjects.

KW - Cross-over designs

KW - Repeated measurement designs

KW - Interference models

KW - Optimal design

KW - Total effects

U2 - 10.1214/14-AOS1247

DO - 10.1214/14-AOS1247

M3 - Article

SN - 0090-5364

VL - 42

SP - 2282

EP - 2300

JO - Annals of Statistics

JF - Annals of Statistics

IS - 6

ER -

Optimal cross-over designs for full interaction models

Abstract

Keywords

Access to Document

Fingerprint

Profiles

R. A. Bailey

Cite this