Separation of individual-level and cluster-level covariate effects in regression analysis of correlated data

Melissa D. Begg, Michael K. Parides

Research output: Contribution to journalReview article

193 Citations (Scopus)

Abstract

The focus of this paper is regression analysis of clustered data. Although the presence of intracluster correlation (the tendency for items within a cluster to respond alike) is typically viewed as an obstacle to good inference, the complex structure of clustered data offers significant analytic advantages over independent data. One key advantage is the ability to separate effects at the individual (or item-specific) level and the group (or cluster-specific) level. We review different approaches for the separation of individual-level and cluster-level effects on response, their appropriate interpretation and give recommendations for model fitting based on the intent of the data analyst. Unlike many earlier papers on this topic, we place particular emphasis on the interpretation of the cluster-level covariate effect. The main ideas of the paper are highlighted in an analysis of the relationship between birth weight and IQ using sibling data from a large birth cohort study.

Original languageEnglish (US)
Pages (from-to)2591-2602
Number of pages12
JournalStatistics in Medicine
Volume22
Issue number16
DOIs
StatePublished - Aug 30 2003
Externally publishedYes

Fingerprint

Correlated Data
Regression Analysis
Birth Weight
Covariates
Cohort Studies
Parturition
Clustered Data
Intracluster Correlation
Cohort Study
Alike
Model Fitting
Complex Structure
Recommendations
Interpretation

Keywords

  • Between-cluster effects
  • Clustered data analysis
  • Covariate selection
  • Model misspecification
  • Within-cluster effects

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Separation of individual-level and cluster-level covariate effects in regression analysis of correlated data. / Begg, Melissa D.; Parides, Michael K.

In: Statistics in Medicine, Vol. 22, No. 16, 30.08.2003, p. 2591-2602.

Research output: Contribution to journalReview article

@article{861b6e70d85742418b9e9c21bc087c33,
title = "Separation of individual-level and cluster-level covariate effects in regression analysis of correlated data",
abstract = "The focus of this paper is regression analysis of clustered data. Although the presence of intracluster correlation (the tendency for items within a cluster to respond alike) is typically viewed as an obstacle to good inference, the complex structure of clustered data offers significant analytic advantages over independent data. One key advantage is the ability to separate effects at the individual (or item-specific) level and the group (or cluster-specific) level. We review different approaches for the separation of individual-level and cluster-level effects on response, their appropriate interpretation and give recommendations for model fitting based on the intent of the data analyst. Unlike many earlier papers on this topic, we place particular emphasis on the interpretation of the cluster-level covariate effect. The main ideas of the paper are highlighted in an analysis of the relationship between birth weight and IQ using sibling data from a large birth cohort study.",
keywords = "Between-cluster effects, Clustered data analysis, Covariate selection, Model misspecification, Within-cluster effects",
author = "Begg, {Melissa D.} and Parides, {Michael K.}",
year = "2003",
month = "8",
day = "30",
doi = "10.1002/sim.1524",
language = "English (US)",
volume = "22",
pages = "2591--2602",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "16",

}

TY - JOUR

T1 - Separation of individual-level and cluster-level covariate effects in regression analysis of correlated data

AU - Begg, Melissa D.

AU - Parides, Michael K.

PY - 2003/8/30

Y1 - 2003/8/30

N2 - The focus of this paper is regression analysis of clustered data. Although the presence of intracluster correlation (the tendency for items within a cluster to respond alike) is typically viewed as an obstacle to good inference, the complex structure of clustered data offers significant analytic advantages over independent data. One key advantage is the ability to separate effects at the individual (or item-specific) level and the group (or cluster-specific) level. We review different approaches for the separation of individual-level and cluster-level effects on response, their appropriate interpretation and give recommendations for model fitting based on the intent of the data analyst. Unlike many earlier papers on this topic, we place particular emphasis on the interpretation of the cluster-level covariate effect. The main ideas of the paper are highlighted in an analysis of the relationship between birth weight and IQ using sibling data from a large birth cohort study.

AB - The focus of this paper is regression analysis of clustered data. Although the presence of intracluster correlation (the tendency for items within a cluster to respond alike) is typically viewed as an obstacle to good inference, the complex structure of clustered data offers significant analytic advantages over independent data. One key advantage is the ability to separate effects at the individual (or item-specific) level and the group (or cluster-specific) level. We review different approaches for the separation of individual-level and cluster-level effects on response, their appropriate interpretation and give recommendations for model fitting based on the intent of the data analyst. Unlike many earlier papers on this topic, we place particular emphasis on the interpretation of the cluster-level covariate effect. The main ideas of the paper are highlighted in an analysis of the relationship between birth weight and IQ using sibling data from a large birth cohort study.

KW - Between-cluster effects

KW - Clustered data analysis

KW - Covariate selection

KW - Model misspecification

KW - Within-cluster effects

UR - http://www.scopus.com/inward/record.url?scp=0041565373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041565373&partnerID=8YFLogxK

U2 - 10.1002/sim.1524

DO - 10.1002/sim.1524

M3 - Review article

C2 - 12898546

AN - SCOPUS:0041565373

VL - 22

SP - 2591

EP - 2602

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 16

ER -