Doubly Robust Estimates for Binary Longitudinal Data Analysis with Missing Response and Missing Covariates

Baojiang Chen, Xiao Hua Zhou

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Longitudinal studies often feature incomplete response and covariate data. Likelihood-based methods such as the expectation-maximization algorithm give consistent estimators for model parameters when data are missing at random (MAR) provided that the response model and the missing covariate model are correctly specified; however, we do not need to specify the missing data mechanism. An alternative method is the weighted estimating equation, which gives consistent estimators if the missing data and response models are correctly specified; however, we do not need to specify the distribution of the covariates that have missing values. In this article, we develop a doubly robust estimation method for longitudinal data with missing response and missing covariate when data are MAR. This method is appealing in that it can provide consistent estimators if either the missing data model or the missing covariate model is correctly specified. Simulation studies demonstrate that this method performs well in a variety of situations.

Original languageEnglish (US)
Pages (from-to)830-842
Number of pages13
JournalBiometrics
Volume67
Issue number3
DOIs
StatePublished - Sep 1 2011

Fingerprint

Longitudinal Data Analysis
Missing Covariates
Robust Estimate
Binary Data
data analysis
Consistent Estimator
Missing at Random
Missing Data
Covariates
Weighted Estimating Equations
Missing Data Mechanism
Model
Longitudinal Study
Robust Estimation
Missing Values
Expectation-maximization Algorithm
Longitudinal Data
methodology
Data Model
Longitudinal Studies

Keywords

  • Doubly robust
  • Estimating equation
  • Missing at random
  • Missing covariate
  • Missing response

ASJC Scopus subject areas

  • Statistics and Probability
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Agricultural and Biological Sciences(all)
  • Applied Mathematics

Cite this

Doubly Robust Estimates for Binary Longitudinal Data Analysis with Missing Response and Missing Covariates. / Chen, Baojiang; Zhou, Xiao Hua.

In: Biometrics, Vol. 67, No. 3, 01.09.2011, p. 830-842.

Research output: Contribution to journalArticle

Chen, Baojiang ; Zhou, Xiao Hua. / Doubly Robust Estimates for Binary Longitudinal Data Analysis with Missing Response and Missing Covariates. In: Biometrics. 2011 ; Vol. 67, No. 3. pp. 830-842.
@article{3b4662d8731648b292045fc5f0600b8e,
title = "Doubly Robust Estimates for Binary Longitudinal Data Analysis with Missing Response and Missing Covariates",
abstract = "Longitudinal studies often feature incomplete response and covariate data. Likelihood-based methods such as the expectation-maximization algorithm give consistent estimators for model parameters when data are missing at random (MAR) provided that the response model and the missing covariate model are correctly specified; however, we do not need to specify the missing data mechanism. An alternative method is the weighted estimating equation, which gives consistent estimators if the missing data and response models are correctly specified; however, we do not need to specify the distribution of the covariates that have missing values. In this article, we develop a doubly robust estimation method for longitudinal data with missing response and missing covariate when data are MAR. This method is appealing in that it can provide consistent estimators if either the missing data model or the missing covariate model is correctly specified. Simulation studies demonstrate that this method performs well in a variety of situations.",
keywords = "Doubly robust, Estimating equation, Missing at random, Missing covariate, Missing response",
author = "Baojiang Chen and Zhou, {Xiao Hua}",
year = "2011",
month = "9",
day = "1",
doi = "10.1111/j.1541-0420.2010.01541.x",
language = "English (US)",
volume = "67",
pages = "830--842",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Doubly Robust Estimates for Binary Longitudinal Data Analysis with Missing Response and Missing Covariates

AU - Chen, Baojiang

AU - Zhou, Xiao Hua

PY - 2011/9/1

Y1 - 2011/9/1

N2 - Longitudinal studies often feature incomplete response and covariate data. Likelihood-based methods such as the expectation-maximization algorithm give consistent estimators for model parameters when data are missing at random (MAR) provided that the response model and the missing covariate model are correctly specified; however, we do not need to specify the missing data mechanism. An alternative method is the weighted estimating equation, which gives consistent estimators if the missing data and response models are correctly specified; however, we do not need to specify the distribution of the covariates that have missing values. In this article, we develop a doubly robust estimation method for longitudinal data with missing response and missing covariate when data are MAR. This method is appealing in that it can provide consistent estimators if either the missing data model or the missing covariate model is correctly specified. Simulation studies demonstrate that this method performs well in a variety of situations.

AB - Longitudinal studies often feature incomplete response and covariate data. Likelihood-based methods such as the expectation-maximization algorithm give consistent estimators for model parameters when data are missing at random (MAR) provided that the response model and the missing covariate model are correctly specified; however, we do not need to specify the missing data mechanism. An alternative method is the weighted estimating equation, which gives consistent estimators if the missing data and response models are correctly specified; however, we do not need to specify the distribution of the covariates that have missing values. In this article, we develop a doubly robust estimation method for longitudinal data with missing response and missing covariate when data are MAR. This method is appealing in that it can provide consistent estimators if either the missing data model or the missing covariate model is correctly specified. Simulation studies demonstrate that this method performs well in a variety of situations.

KW - Doubly robust

KW - Estimating equation

KW - Missing at random

KW - Missing covariate

KW - Missing response

UR - http://www.scopus.com/inward/record.url?scp=80052808295&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052808295&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2010.01541.x

DO - 10.1111/j.1541-0420.2010.01541.x

M3 - Article

C2 - 21281272

AN - SCOPUS:80052808295

VL - 67

SP - 830

EP - 842

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 3

ER -