Statistical analysis of correlated data using generalized estimating equations: An orientation

James A. Hanley, Abdissa Negassa, Michael D deB Edwardes, Janet E. Forrester

Research output: Contribution to journalArticle

1313 Citations (Scopus)

Abstract

The method of generalized estimating equations (GEE) is often used to analyze longitudinal and other correlated response data, particularly if responses are binary. However, few descriptions of the method are accessible to epidemiologists. In this paper, the authors use small worked examples and one real data set, involving both binary and quantitative response data, to help end-users appreciate the essence of the method. The examples are simple enough to see the behind-the-scenes calculations and the essential role of weighted observations, and they allow nonstatisticians to imagine the calculations involved when the GEE method is applied to more complex multivariate data.

Original languageEnglish (US)
Pages (from-to)364-375
Number of pages12
JournalAmerican Journal of Epidemiology
Volume157
Issue number4
DOIs
StatePublished - Feb 15 2003

Fingerprint

Statistical Data Interpretation

Keywords

  • Correlation
  • Epidemiologic methods
  • Generalized estimating equation
  • Longitudinal studies
  • Odds ratio
  • Statistics

ASJC Scopus subject areas

  • Epidemiology

Cite this

Statistical analysis of correlated data using generalized estimating equations : An orientation. / Hanley, James A.; Negassa, Abdissa; Edwardes, Michael D deB; Forrester, Janet E.

In: American Journal of Epidemiology, Vol. 157, No. 4, 15.02.2003, p. 364-375.

Research output: Contribution to journalArticle

Hanley, James A. ; Negassa, Abdissa ; Edwardes, Michael D deB ; Forrester, Janet E. / Statistical analysis of correlated data using generalized estimating equations : An orientation. In: American Journal of Epidemiology. 2003 ; Vol. 157, No. 4. pp. 364-375.
@article{f84a15a36c734cb486fd98b2e2ea0f47,
title = "Statistical analysis of correlated data using generalized estimating equations: An orientation",
abstract = "The method of generalized estimating equations (GEE) is often used to analyze longitudinal and other correlated response data, particularly if responses are binary. However, few descriptions of the method are accessible to epidemiologists. In this paper, the authors use small worked examples and one real data set, involving both binary and quantitative response data, to help end-users appreciate the essence of the method. The examples are simple enough to see the behind-the-scenes calculations and the essential role of weighted observations, and they allow nonstatisticians to imagine the calculations involved when the GEE method is applied to more complex multivariate data.",
keywords = "Correlation, Epidemiologic methods, Generalized estimating equation, Longitudinal studies, Odds ratio, Statistics",
author = "Hanley, {James A.} and Abdissa Negassa and Edwardes, {Michael D deB} and Forrester, {Janet E.}",
year = "2003",
month = "2",
day = "15",
doi = "10.1093/aje/kwf215",
language = "English (US)",
volume = "157",
pages = "364--375",
journal = "American Journal of Epidemiology",
issn = "0002-9262",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - Statistical analysis of correlated data using generalized estimating equations

T2 - An orientation

AU - Hanley, James A.

AU - Negassa, Abdissa

AU - Edwardes, Michael D deB

AU - Forrester, Janet E.

PY - 2003/2/15

Y1 - 2003/2/15

N2 - The method of generalized estimating equations (GEE) is often used to analyze longitudinal and other correlated response data, particularly if responses are binary. However, few descriptions of the method are accessible to epidemiologists. In this paper, the authors use small worked examples and one real data set, involving both binary and quantitative response data, to help end-users appreciate the essence of the method. The examples are simple enough to see the behind-the-scenes calculations and the essential role of weighted observations, and they allow nonstatisticians to imagine the calculations involved when the GEE method is applied to more complex multivariate data.

AB - The method of generalized estimating equations (GEE) is often used to analyze longitudinal and other correlated response data, particularly if responses are binary. However, few descriptions of the method are accessible to epidemiologists. In this paper, the authors use small worked examples and one real data set, involving both binary and quantitative response data, to help end-users appreciate the essence of the method. The examples are simple enough to see the behind-the-scenes calculations and the essential role of weighted observations, and they allow nonstatisticians to imagine the calculations involved when the GEE method is applied to more complex multivariate data.

KW - Correlation

KW - Epidemiologic methods

KW - Generalized estimating equation

KW - Longitudinal studies

KW - Odds ratio

KW - Statistics

UR - http://www.scopus.com/inward/record.url?scp=0037441919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037441919&partnerID=8YFLogxK

U2 - 10.1093/aje/kwf215

DO - 10.1093/aje/kwf215

M3 - Article

C2 - 12578807

AN - SCOPUS:0037441919

VL - 157

SP - 364

EP - 375

JO - American Journal of Epidemiology

JF - American Journal of Epidemiology

SN - 0002-9262

IS - 4

ER -