Effect of regression to the mean in the presence of within‐subject variability

William D. Johnson, Varghese George

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

Regression to the mean arises often in statistical applications where the units chosen for study relate to some observed characteristic in the extreme of its distribution. Gardner and Heady attribute the effect of regression to the mean to measurement errors. They assume the modelYi = U + ei, where U is a fixed within‐subject component and ei is the random measurement error. They suggest several replicate measurements to reduce the regression effect under the assumption that the measurement errors ei are independent within subjects. While measurement errors play an important role in regression to the mean, one should not overlook within‐subject variation. In this paper, we consider a model to estimate the regression effect in the presence of correlated within‐subject effects as well as independent measurement errors.

Original languageEnglish (US)
Pages (from-to)1295-1302
Number of pages8
JournalStatistics in Medicine
Volume10
Issue number8
DOIs
StatePublished - Jan 1 1991
Externally publishedYes

Fingerprint

Measurement Error
Regression
Regression Effects
Random Error
Extremes
Attribute
Unit
Estimate

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Effect of regression to the mean in the presence of within‐subject variability. / Johnson, William D.; George, Varghese.

In: Statistics in Medicine, Vol. 10, No. 8, 01.01.1991, p. 1295-1302.

Research output: Contribution to journalArticle

@article{226dd07aea2a463f9e2975bd2c10538e,
title = "Effect of regression to the mean in the presence of within‐subject variability",
abstract = "Regression to the mean arises often in statistical applications where the units chosen for study relate to some observed characteristic in the extreme of its distribution. Gardner and Heady attribute the effect of regression to the mean to measurement errors. They assume the modelYi = U + ei, where U is a fixed within‐subject component and ei is the random measurement error. They suggest several replicate measurements to reduce the regression effect under the assumption that the measurement errors ei are independent within subjects. While measurement errors play an important role in regression to the mean, one should not overlook within‐subject variation. In this paper, we consider a model to estimate the regression effect in the presence of correlated within‐subject effects as well as independent measurement errors.",
author = "Johnson, {William D.} and Varghese George",
year = "1991",
month = "1",
day = "1",
doi = "10.1002/sim.4780100812",
language = "English (US)",
volume = "10",
pages = "1295--1302",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "8",

}

TY - JOUR

T1 - Effect of regression to the mean in the presence of within‐subject variability

AU - Johnson, William D.

AU - George, Varghese

PY - 1991/1/1

Y1 - 1991/1/1

N2 - Regression to the mean arises often in statistical applications where the units chosen for study relate to some observed characteristic in the extreme of its distribution. Gardner and Heady attribute the effect of regression to the mean to measurement errors. They assume the modelYi = U + ei, where U is a fixed within‐subject component and ei is the random measurement error. They suggest several replicate measurements to reduce the regression effect under the assumption that the measurement errors ei are independent within subjects. While measurement errors play an important role in regression to the mean, one should not overlook within‐subject variation. In this paper, we consider a model to estimate the regression effect in the presence of correlated within‐subject effects as well as independent measurement errors.

AB - Regression to the mean arises often in statistical applications where the units chosen for study relate to some observed characteristic in the extreme of its distribution. Gardner and Heady attribute the effect of regression to the mean to measurement errors. They assume the modelYi = U + ei, where U is a fixed within‐subject component and ei is the random measurement error. They suggest several replicate measurements to reduce the regression effect under the assumption that the measurement errors ei are independent within subjects. While measurement errors play an important role in regression to the mean, one should not overlook within‐subject variation. In this paper, we consider a model to estimate the regression effect in the presence of correlated within‐subject effects as well as independent measurement errors.

UR - http://www.scopus.com/inward/record.url?scp=0025833409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025833409&partnerID=8YFLogxK

U2 - 10.1002/sim.4780100812

DO - 10.1002/sim.4780100812

M3 - Article

C2 - 1925160

AN - SCOPUS:0025833409

VL - 10

SP - 1295

EP - 1302

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 8

ER -