Marginal methods for clustered longitudinal binary data with incomplete covariates

Baojiang Chen, Grace Y. Yi, Richard J. Cook, Xiao Hua Zhou

Research output: Contribution to journalArticle

Abstract

Many analyses for incomplete longitudinal data are directed to examining the impact of covariates on the marginal mean responses. We consider the setting in which longitudinal responses are collected from individuals nested within clusters. We discuss methods for assessing covariate effects on the mean and association parameters when covariates are incompletely observed. Weighted first and second order estimating equations are constructed to obtain consistent estimates of mean and association parameters when covariates are missing at random. Empirical studies demonstrate that estimators from the proposed method have negligible finite sample biases in moderate samples. An application to the National Alzheimer's Coordinating Center (NACC) Uniform Data Set (UDS) demonstrates the utility of the proposed method.

Original languageEnglish (US)
Pages (from-to)2819-2831
Number of pages13
JournalJournal of Statistical Planning and Inference
Volume142
Issue number10
DOIs
StatePublished - Oct 1 2012

Fingerprint

Binary Data
Longitudinal Data
Covariates
Consistent Estimates
Missing at Random
Estimating Equation
Incomplete Data
Second Order Equations
Empirical Study
Demonstrate
First-order
Estimator

Keywords

  • Association
  • Generalized estimating equation
  • Longitudinal data
  • Missing covariates

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

Marginal methods for clustered longitudinal binary data with incomplete covariates. / Chen, Baojiang; Yi, Grace Y.; Cook, Richard J.; Zhou, Xiao Hua.

In: Journal of Statistical Planning and Inference, Vol. 142, No. 10, 01.10.2012, p. 2819-2831.

Research output: Contribution to journalArticle

Chen, Baojiang ; Yi, Grace Y. ; Cook, Richard J. ; Zhou, Xiao Hua. / Marginal methods for clustered longitudinal binary data with incomplete covariates. In: Journal of Statistical Planning and Inference. 2012 ; Vol. 142, No. 10. pp. 2819-2831.
@article{645b33ddce604f7395108f567acab924,
title = "Marginal methods for clustered longitudinal binary data with incomplete covariates",
abstract = "Many analyses for incomplete longitudinal data are directed to examining the impact of covariates on the marginal mean responses. We consider the setting in which longitudinal responses are collected from individuals nested within clusters. We discuss methods for assessing covariate effects on the mean and association parameters when covariates are incompletely observed. Weighted first and second order estimating equations are constructed to obtain consistent estimates of mean and association parameters when covariates are missing at random. Empirical studies demonstrate that estimators from the proposed method have negligible finite sample biases in moderate samples. An application to the National Alzheimer's Coordinating Center (NACC) Uniform Data Set (UDS) demonstrates the utility of the proposed method.",
keywords = "Association, Generalized estimating equation, Longitudinal data, Missing covariates",
author = "Baojiang Chen and Yi, {Grace Y.} and Cook, {Richard J.} and Zhou, {Xiao Hua}",
year = "2012",
month = "10",
day = "1",
doi = "10.1016/j.jspi.2012.04.006",
language = "English (US)",
volume = "142",
pages = "2819--2831",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "10",

}

TY - JOUR

T1 - Marginal methods for clustered longitudinal binary data with incomplete covariates

AU - Chen, Baojiang

AU - Yi, Grace Y.

AU - Cook, Richard J.

AU - Zhou, Xiao Hua

PY - 2012/10/1

Y1 - 2012/10/1

N2 - Many analyses for incomplete longitudinal data are directed to examining the impact of covariates on the marginal mean responses. We consider the setting in which longitudinal responses are collected from individuals nested within clusters. We discuss methods for assessing covariate effects on the mean and association parameters when covariates are incompletely observed. Weighted first and second order estimating equations are constructed to obtain consistent estimates of mean and association parameters when covariates are missing at random. Empirical studies demonstrate that estimators from the proposed method have negligible finite sample biases in moderate samples. An application to the National Alzheimer's Coordinating Center (NACC) Uniform Data Set (UDS) demonstrates the utility of the proposed method.

AB - Many analyses for incomplete longitudinal data are directed to examining the impact of covariates on the marginal mean responses. We consider the setting in which longitudinal responses are collected from individuals nested within clusters. We discuss methods for assessing covariate effects on the mean and association parameters when covariates are incompletely observed. Weighted first and second order estimating equations are constructed to obtain consistent estimates of mean and association parameters when covariates are missing at random. Empirical studies demonstrate that estimators from the proposed method have negligible finite sample biases in moderate samples. An application to the National Alzheimer's Coordinating Center (NACC) Uniform Data Set (UDS) demonstrates the utility of the proposed method.

KW - Association

KW - Generalized estimating equation

KW - Longitudinal data

KW - Missing covariates

UR - http://www.scopus.com/inward/record.url?scp=84861528574&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861528574&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2012.04.006

DO - 10.1016/j.jspi.2012.04.006

M3 - Article

VL - 142

SP - 2819

EP - 2831

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 10

ER -