Optimal crossover designs when carryover effects are proportional to direct effects

Mausumi Bose, John Stufken

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Crossover designs are used for a variety of different applications. While these designs have a number of attractive features, they also induce a number of special problems and concerns. One of these is the possible presence of carryover effects. Even with the use of washout periods, which are for many applications widely accepted as an indispensable component, the effect of a treatment from a previous period may not be completely eliminated. A model that has recently received renewed attention in the literature is the model in which first-order carryover effects are assumed to be proportional to direct treatment effects. Under this model, assuming that the constant of proportionality is known, we identify optimal and efficient designs for the direct effects for different values of the constant of proportionality. We also consider the implication of these results for the case that the constant of proportionality is not known.

Original languageEnglish (US)
Pages (from-to)3291-3302
Number of pages12
JournalJournal of Statistical Planning and Inference
Volume137
Issue number11
DOIs
StatePublished - Nov 1 2007
Externally publishedYes

Fingerprint

Carry-over Effects
Design Effect
Crossover Design
Direct Effect
Directly proportional
Treatment Effects
Model
First-order
Direct effect
Crossover
Proportionality
Optimal design
Design

Keywords

  • Direct treatment effects
  • Proportional carryover effects
  • Universal optimality

ASJC Scopus subject areas

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

Cite this

Optimal crossover designs when carryover effects are proportional to direct effects. / Bose, Mausumi; Stufken, John.

In: Journal of Statistical Planning and Inference, Vol. 137, No. 11, 01.11.2007, p. 3291-3302.

Research output: Contribution to journalArticle

@article{4e5cc25b040248ebb35e0b0ff1cbd636,
title = "Optimal crossover designs when carryover effects are proportional to direct effects",
abstract = "Crossover designs are used for a variety of different applications. While these designs have a number of attractive features, they also induce a number of special problems and concerns. One of these is the possible presence of carryover effects. Even with the use of washout periods, which are for many applications widely accepted as an indispensable component, the effect of a treatment from a previous period may not be completely eliminated. A model that has recently received renewed attention in the literature is the model in which first-order carryover effects are assumed to be proportional to direct treatment effects. Under this model, assuming that the constant of proportionality is known, we identify optimal and efficient designs for the direct effects for different values of the constant of proportionality. We also consider the implication of these results for the case that the constant of proportionality is not known.",
keywords = "Direct treatment effects, Proportional carryover effects, Universal optimality",
author = "Mausumi Bose and John Stufken",
year = "2007",
month = "11",
day = "1",
doi = "10.1016/j.jspi.2007.03.012",
language = "English (US)",
volume = "137",
pages = "3291--3302",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "11",

}

TY - JOUR

T1 - Optimal crossover designs when carryover effects are proportional to direct effects

AU - Bose, Mausumi

AU - Stufken, John

PY - 2007/11/1

Y1 - 2007/11/1

N2 - Crossover designs are used for a variety of different applications. While these designs have a number of attractive features, they also induce a number of special problems and concerns. One of these is the possible presence of carryover effects. Even with the use of washout periods, which are for many applications widely accepted as an indispensable component, the effect of a treatment from a previous period may not be completely eliminated. A model that has recently received renewed attention in the literature is the model in which first-order carryover effects are assumed to be proportional to direct treatment effects. Under this model, assuming that the constant of proportionality is known, we identify optimal and efficient designs for the direct effects for different values of the constant of proportionality. We also consider the implication of these results for the case that the constant of proportionality is not known.

AB - Crossover designs are used for a variety of different applications. While these designs have a number of attractive features, they also induce a number of special problems and concerns. One of these is the possible presence of carryover effects. Even with the use of washout periods, which are for many applications widely accepted as an indispensable component, the effect of a treatment from a previous period may not be completely eliminated. A model that has recently received renewed attention in the literature is the model in which first-order carryover effects are assumed to be proportional to direct treatment effects. Under this model, assuming that the constant of proportionality is known, we identify optimal and efficient designs for the direct effects for different values of the constant of proportionality. We also consider the implication of these results for the case that the constant of proportionality is not known.

KW - Direct treatment effects

KW - Proportional carryover effects

KW - Universal optimality

UR - http://www.scopus.com/inward/record.url?scp=34447504423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34447504423&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2007.03.012

DO - 10.1016/j.jspi.2007.03.012

M3 - Article

AN - SCOPUS:34447504423

VL - 137

SP - 3291

EP - 3302

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 11

ER -