Joint generalized estimating equations for multivariate longitudinal binary outcomes with missing data: An application to acquired immune deficiency syndrome data

Stuart R. Lipsitz, Garrett M. Fitzmaurice, Joseph G. Ibrahim, Debajyoti Sinha, Michael Parzen, Steven E Lipshultz

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

In a large, prospective longitudinal study designed to monitor cardiac abnormalities in children born to women who are infected with the human immunodeficiency virus, instead of a single outcome variable, there are multiple binary outcomes (e.g. abnormal heart rate, abnormal blood pressure and abnormal heart wall thickness) considered as joint measures of heart function over time. In the presence of missing responses at some time points, longitudinal marginal models for these multiple outcomes can be estimated by using generalized estimating equations (GEEs), and consistent estimates can be obtained under the assumption of a missingness completely at random mechanism. When the missing data mechanism is missingness at random, i.e. the probability of missing a particular outcome at a time point depends on observed values of that outcome and the remaining outcomes at other time points, we propose joint estimation of the marginal models by using a single modified GEE based on an EM-type algorithm. The method proposed is motivated by the longitudinal study of cardiac abnormalities in children who were born to women infected with the human immunodeficiency virus, and analyses of these data are presented to illustrate the application of the method. Further, in an asymptotic study of bias, we show that, under a missingness at random mechanism in which missingness depends on all observed outcome variables, our joint estimation via the modified GEE produces almost unbiased estimates, provided that the correlation model has been correctly specified, whereas estimates from standard GEEs can lead to substantial bias.

Original languageEnglish
Pages (from-to)3-20
Number of pages18
JournalJournal of the Royal Statistical Society. Series A: Statistics in Society
Volume172
Issue number1
DOIs
StatePublished - Jan 1 2009

Fingerprint

Binary Outcomes
Generalized Estimating Equations
Missing Data
Multiple Outcomes
Marginal Model
Longitudinal Study
longitudinal study
Cardiac
Virus
Missing Data Mechanism
trend
Consistent Estimates
Blood Pressure
Heart Rate
Estimate
Monitor
time
Generalized estimating equations
Missing data
Values

Keywords

  • EM-type algorithm
  • Generalized estimating equations
  • Missingness at random
  • Missingness completely at random

ASJC Scopus subject areas

  • Statistics and Probability
  • Economics and Econometrics
  • Social Sciences (miscellaneous)
  • Statistics, Probability and Uncertainty

Cite this

Joint generalized estimating equations for multivariate longitudinal binary outcomes with missing data : An application to acquired immune deficiency syndrome data. / Lipsitz, Stuart R.; Fitzmaurice, Garrett M.; Ibrahim, Joseph G.; Sinha, Debajyoti; Parzen, Michael; Lipshultz, Steven E.

In: Journal of the Royal Statistical Society. Series A: Statistics in Society, Vol. 172, No. 1, 01.01.2009, p. 3-20.

Research output: Contribution to journalArticle

Lipsitz, Stuart R. ; Fitzmaurice, Garrett M. ; Ibrahim, Joseph G. ; Sinha, Debajyoti ; Parzen, Michael ; Lipshultz, Steven E. / Joint generalized estimating equations for multivariate longitudinal binary outcomes with missing data : An application to acquired immune deficiency syndrome data. In: Journal of the Royal Statistical Society. Series A: Statistics in Society. 2009 ; Vol. 172, No. 1. pp. 3-20.
@article{e486fa03681c4a7ca4fa657770a63c73,
title = "Joint generalized estimating equations for multivariate longitudinal binary outcomes with missing data: An application to acquired immune deficiency syndrome data",
abstract = "In a large, prospective longitudinal study designed to monitor cardiac abnormalities in children born to women who are infected with the human immunodeficiency virus, instead of a single outcome variable, there are multiple binary outcomes (e.g. abnormal heart rate, abnormal blood pressure and abnormal heart wall thickness) considered as joint measures of heart function over time. In the presence of missing responses at some time points, longitudinal marginal models for these multiple outcomes can be estimated by using generalized estimating equations (GEEs), and consistent estimates can be obtained under the assumption of a missingness completely at random mechanism. When the missing data mechanism is missingness at random, i.e. the probability of missing a particular outcome at a time point depends on observed values of that outcome and the remaining outcomes at other time points, we propose joint estimation of the marginal models by using a single modified GEE based on an EM-type algorithm. The method proposed is motivated by the longitudinal study of cardiac abnormalities in children who were born to women infected with the human immunodeficiency virus, and analyses of these data are presented to illustrate the application of the method. Further, in an asymptotic study of bias, we show that, under a missingness at random mechanism in which missingness depends on all observed outcome variables, our joint estimation via the modified GEE produces almost unbiased estimates, provided that the correlation model has been correctly specified, whereas estimates from standard GEEs can lead to substantial bias.",
keywords = "EM-type algorithm, Generalized estimating equations, Missingness at random, Missingness completely at random",
author = "Lipsitz, {Stuart R.} and Fitzmaurice, {Garrett M.} and Ibrahim, {Joseph G.} and Debajyoti Sinha and Michael Parzen and Lipshultz, {Steven E}",
year = "2009",
month = "1",
day = "1",
doi = "10.1111/j.1467-985X.2008.00564.x",
language = "English",
volume = "172",
pages = "3--20",
journal = "Journal of the Royal Statistical Society. Series A: Statistics in Society",
issn = "0964-1998",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Joint generalized estimating equations for multivariate longitudinal binary outcomes with missing data

T2 - An application to acquired immune deficiency syndrome data

AU - Lipsitz, Stuart R.

AU - Fitzmaurice, Garrett M.

AU - Ibrahim, Joseph G.

AU - Sinha, Debajyoti

AU - Parzen, Michael

AU - Lipshultz, Steven E

PY - 2009/1/1

Y1 - 2009/1/1

N2 - In a large, prospective longitudinal study designed to monitor cardiac abnormalities in children born to women who are infected with the human immunodeficiency virus, instead of a single outcome variable, there are multiple binary outcomes (e.g. abnormal heart rate, abnormal blood pressure and abnormal heart wall thickness) considered as joint measures of heart function over time. In the presence of missing responses at some time points, longitudinal marginal models for these multiple outcomes can be estimated by using generalized estimating equations (GEEs), and consistent estimates can be obtained under the assumption of a missingness completely at random mechanism. When the missing data mechanism is missingness at random, i.e. the probability of missing a particular outcome at a time point depends on observed values of that outcome and the remaining outcomes at other time points, we propose joint estimation of the marginal models by using a single modified GEE based on an EM-type algorithm. The method proposed is motivated by the longitudinal study of cardiac abnormalities in children who were born to women infected with the human immunodeficiency virus, and analyses of these data are presented to illustrate the application of the method. Further, in an asymptotic study of bias, we show that, under a missingness at random mechanism in which missingness depends on all observed outcome variables, our joint estimation via the modified GEE produces almost unbiased estimates, provided that the correlation model has been correctly specified, whereas estimates from standard GEEs can lead to substantial bias.

AB - In a large, prospective longitudinal study designed to monitor cardiac abnormalities in children born to women who are infected with the human immunodeficiency virus, instead of a single outcome variable, there are multiple binary outcomes (e.g. abnormal heart rate, abnormal blood pressure and abnormal heart wall thickness) considered as joint measures of heart function over time. In the presence of missing responses at some time points, longitudinal marginal models for these multiple outcomes can be estimated by using generalized estimating equations (GEEs), and consistent estimates can be obtained under the assumption of a missingness completely at random mechanism. When the missing data mechanism is missingness at random, i.e. the probability of missing a particular outcome at a time point depends on observed values of that outcome and the remaining outcomes at other time points, we propose joint estimation of the marginal models by using a single modified GEE based on an EM-type algorithm. The method proposed is motivated by the longitudinal study of cardiac abnormalities in children who were born to women infected with the human immunodeficiency virus, and analyses of these data are presented to illustrate the application of the method. Further, in an asymptotic study of bias, we show that, under a missingness at random mechanism in which missingness depends on all observed outcome variables, our joint estimation via the modified GEE produces almost unbiased estimates, provided that the correlation model has been correctly specified, whereas estimates from standard GEEs can lead to substantial bias.

KW - EM-type algorithm

KW - Generalized estimating equations

KW - Missingness at random

KW - Missingness completely at random

UR - http://www.scopus.com/inward/record.url?scp=57849118330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57849118330&partnerID=8YFLogxK

U2 - 10.1111/j.1467-985X.2008.00564.x

DO - 10.1111/j.1467-985X.2008.00564.x

M3 - Article

AN - SCOPUS:57849118330

VL - 172

SP - 3

EP - 20

JO - Journal of the Royal Statistical Society. Series A: Statistics in Society

JF - Journal of the Royal Statistical Society. Series A: Statistics in Society

SN - 0964-1998

IS - 1

ER -