A Robust Analysis of Crossover Designs using Multisample Generalized L-Statistics

Mary E. Putt, Vernon M. Chinchilli

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In a crossover study, some or all subjects receive more than one treatment sequentially. Using a clinical example as motivation, we develop multisample generalized L-statistics (GL-statistics) to estimate and test for treatment effects in crossovers when the distribution of the response data deviates from normality. The basic idea is to adapt simple L-statistics, such as the trimmed mean and median, to data with dependencies. GL-statistics may be applied to crossovers with more than two periods and/or sequences. These designs are useful for experiments with two treatments in which carryover and treatment effects might be aliased in the commonly used two-period, two-sequence design, as well as for experiments with more than two treatments. For data analysis with large samples, the asymptotic properties of the GL-statistics suggest that the generalized trimmed mean and generalized median often should be strongly consistent and normal. A simulation study of a four-sequence, two-period crossover design found little loss in efficiency relative to a least squares approach when the trimmed mean or median is used with normal data, and substantial gains when the data are nonnormal, particularly for large sample sizes.

Original languageEnglish (US)
Pages (from-to)1256-1262
Number of pages7
JournalJournal of the American Statistical Association
Volume95
Issue number452
DOIs
StatePublished - Dec 1 2000

Fingerprint

L-statistics
Crossover Design
Trimmed Mean
Crossover
Treatment Effects
Carry-over Effects
Relative Efficiency
Normality
Asymptotic Properties
Experiment
Least Squares
Data analysis
Sample Size
Simulation Study
Statistics
Estimate
Median
Design
Treatment effects

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{f8653801c9f04dcda7db914e66d6ab16,
title = "A Robust Analysis of Crossover Designs using Multisample Generalized L-Statistics",
abstract = "In a crossover study, some or all subjects receive more than one treatment sequentially. Using a clinical example as motivation, we develop multisample generalized L-statistics (GL-statistics) to estimate and test for treatment effects in crossovers when the distribution of the response data deviates from normality. The basic idea is to adapt simple L-statistics, such as the trimmed mean and median, to data with dependencies. GL-statistics may be applied to crossovers with more than two periods and/or sequences. These designs are useful for experiments with two treatments in which carryover and treatment effects might be aliased in the commonly used two-period, two-sequence design, as well as for experiments with more than two treatments. For data analysis with large samples, the asymptotic properties of the GL-statistics suggest that the generalized trimmed mean and generalized median often should be strongly consistent and normal. A simulation study of a four-sequence, two-period crossover design found little loss in efficiency relative to a least squares approach when the trimmed mean or median is used with normal data, and substantial gains when the data are nonnormal, particularly for large sample sizes.",
author = "Putt, {Mary E.} and Chinchilli, {Vernon M.}",
year = "2000",
month = "12",
day = "1",
doi = "10.1080/01621459.2000.10474325",
language = "English (US)",
volume = "95",
pages = "1256--1262",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "452",

}

A Robust Analysis of Crossover Designs using Multisample Generalized L-Statistics. / Putt, Mary E.; Chinchilli, Vernon M.

In: Journal of the American Statistical Association, Vol. 95, No. 452, 01.12.2000, p. 1256-1262.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Robust Analysis of Crossover Designs using Multisample Generalized L-Statistics

AU - Putt, Mary E.

AU - Chinchilli, Vernon M.

PY - 2000/12/1

Y1 - 2000/12/1

N2 - In a crossover study, some or all subjects receive more than one treatment sequentially. Using a clinical example as motivation, we develop multisample generalized L-statistics (GL-statistics) to estimate and test for treatment effects in crossovers when the distribution of the response data deviates from normality. The basic idea is to adapt simple L-statistics, such as the trimmed mean and median, to data with dependencies. GL-statistics may be applied to crossovers with more than two periods and/or sequences. These designs are useful for experiments with two treatments in which carryover and treatment effects might be aliased in the commonly used two-period, two-sequence design, as well as for experiments with more than two treatments. For data analysis with large samples, the asymptotic properties of the GL-statistics suggest that the generalized trimmed mean and generalized median often should be strongly consistent and normal. A simulation study of a four-sequence, two-period crossover design found little loss in efficiency relative to a least squares approach when the trimmed mean or median is used with normal data, and substantial gains when the data are nonnormal, particularly for large sample sizes.

AB - In a crossover study, some or all subjects receive more than one treatment sequentially. Using a clinical example as motivation, we develop multisample generalized L-statistics (GL-statistics) to estimate and test for treatment effects in crossovers when the distribution of the response data deviates from normality. The basic idea is to adapt simple L-statistics, such as the trimmed mean and median, to data with dependencies. GL-statistics may be applied to crossovers with more than two periods and/or sequences. These designs are useful for experiments with two treatments in which carryover and treatment effects might be aliased in the commonly used two-period, two-sequence design, as well as for experiments with more than two treatments. For data analysis with large samples, the asymptotic properties of the GL-statistics suggest that the generalized trimmed mean and generalized median often should be strongly consistent and normal. A simulation study of a four-sequence, two-period crossover design found little loss in efficiency relative to a least squares approach when the trimmed mean or median is used with normal data, and substantial gains when the data are nonnormal, particularly for large sample sizes.

UR - http://www.scopus.com/inward/record.url?scp=0442278004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0442278004&partnerID=8YFLogxK

U2 - 10.1080/01621459.2000.10474325

DO - 10.1080/01621459.2000.10474325

M3 - Article

AN - SCOPUS:0442278004

VL - 95

SP - 1256

EP - 1262

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 452

ER -