Longitudinal data analysis using generalized linear models

Kung Yee Liang, Scott Zeger

Research output: Contribution to journalArticle

Abstract

This paper proposes an extension of generalized linear models to the analysis of longitudinal data. We introduce a class of estimating equations that give consistent estimates of the regression parameters and of their variance under mild assumptions about the time dependence. The estimating equations are derived without specifying the joint distribution of a subject's observations yet they reduce to the score equations for niultivariate Gaussian outcomes. Asymptotic theory is presented for the general class of estimators. Specific cases in which we assume independence, m-dependence and exchangeable correlation structures from each subject are discussed. Efficiency of the pioposecl estimators in two simple situations is considered. The approach is closely related to quasi-likelihood.

Original languageEnglish (US)
Pages (from-to)13-22
Number of pages10
JournalBiometrika
Volume73
Issue number1
DOIs
StatePublished - Apr 1986

Fingerprint

Longitudinal Data Analysis
Estimating Equation
Generalized Linear Model
Linear Models
data analysis
M-dependence
linear models
Estimator
Consistent Estimates
Quasi-likelihood
Correlation Structure
Time Dependence
Asymptotic Theory
Longitudinal Data
Joint Distribution
Regression
Class
Generalized linear model
Longitudinal data analysis
Independence

Keywords

  • Estimating equation
  • Generalized linear model
  • Longitudinal data
  • Quasi-likelihood
  • Repeated measures

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Applied Mathematics
  • Mathematics(all)
  • Statistics and Probability
  • Agricultural and Biological Sciences (miscellaneous)
  • Agricultural and Biological Sciences(all)

Cite this

Longitudinal data analysis using generalized linear models. / Liang, Kung Yee; Zeger, Scott.

In: Biometrika, Vol. 73, No. 1, 04.1986, p. 13-22.

Research output: Contribution to journalArticle

Liang, Kung Yee ; Zeger, Scott. / Longitudinal data analysis using generalized linear models. In: Biometrika. 1986 ; Vol. 73, No. 1. pp. 13-22.
@article{f9259cb381b645989ad9a4d867a5809f,
title = "Longitudinal data analysis using generalized linear models",
abstract = "This paper proposes an extension of generalized linear models to the analysis of longitudinal data. We introduce a class of estimating equations that give consistent estimates of the regression parameters and of their variance under mild assumptions about the time dependence. The estimating equations are derived without specifying the joint distribution of a subject's observations yet they reduce to the score equations for niultivariate Gaussian outcomes. Asymptotic theory is presented for the general class of estimators. Specific cases in which we assume independence, m-dependence and exchangeable correlation structures from each subject are discussed. Efficiency of the pioposecl estimators in two simple situations is considered. The approach is closely related to quasi-likelihood.",
keywords = "Estimating equation, Generalized linear model, Longitudinal data, Quasi-likelihood, Repeated measures",
author = "Liang, {Kung Yee} and Scott Zeger",
year = "1986",
month = "4",
doi = "10.1093/biomet/73.1.13",
language = "English (US)",
volume = "73",
pages = "13--22",
journal = "Biometrika",
issn = "0006-3444",
publisher = "Oxford University Press",
number = "1",

}

TY - JOUR

T1 - Longitudinal data analysis using generalized linear models

AU - Liang, Kung Yee

AU - Zeger, Scott

PY - 1986/4

Y1 - 1986/4

N2 - This paper proposes an extension of generalized linear models to the analysis of longitudinal data. We introduce a class of estimating equations that give consistent estimates of the regression parameters and of their variance under mild assumptions about the time dependence. The estimating equations are derived without specifying the joint distribution of a subject's observations yet they reduce to the score equations for niultivariate Gaussian outcomes. Asymptotic theory is presented for the general class of estimators. Specific cases in which we assume independence, m-dependence and exchangeable correlation structures from each subject are discussed. Efficiency of the pioposecl estimators in two simple situations is considered. The approach is closely related to quasi-likelihood.

AB - This paper proposes an extension of generalized linear models to the analysis of longitudinal data. We introduce a class of estimating equations that give consistent estimates of the regression parameters and of their variance under mild assumptions about the time dependence. The estimating equations are derived without specifying the joint distribution of a subject's observations yet they reduce to the score equations for niultivariate Gaussian outcomes. Asymptotic theory is presented for the general class of estimators. Specific cases in which we assume independence, m-dependence and exchangeable correlation structures from each subject are discussed. Efficiency of the pioposecl estimators in two simple situations is considered. The approach is closely related to quasi-likelihood.

KW - Estimating equation

KW - Generalized linear model

KW - Longitudinal data

KW - Quasi-likelihood

KW - Repeated measures

UR - http://www.scopus.com/inward/record.url?scp=77649173768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649173768&partnerID=8YFLogxK

U2 - 10.1093/biomet/73.1.13

DO - 10.1093/biomet/73.1.13

M3 - Article

AN - SCOPUS:77649173768

VL - 73

SP - 13

EP - 22

JO - Biometrika

JF - Biometrika

SN - 0006-3444

IS - 1

ER -