Pseudoempirical-likelihood-based method using calibration for longitudinal data with dropout

Baojiang Chen, Xiao Hua Zhou, Gary Chan

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In observational studies, interest mainly lies in estimation of the population level relationship between the explanatory variables and dependent variables, and the estimation is often undertaken by using a sample of longitudinal data. In some situations, the longitudinal data sample features biases and loss of estimation efficiency due to non-random dropout. However, inclusion of population level information can increase estimation efficiency. We propose an empirical-likelihood-based method to incorporate population level information in a longitudinal study with dropout. The population level information is incorporated via constraints on functions of the parameters, and non-random dropout bias is corrected by using a weighted generalized estimating equations method. We provide a three-step estimation procedure that makes computation easier. Some commonly used methods are compared in simulation studies, which demonstrate that our proposed method can correct the non-random dropout bias and increase the estimation efficiency, especially for small sample sizes or when the missing proportion is high. In some situations, the improvement in efficiency is substantial. Finally, we apply the method to an Alzheimer's disease study.

Original languageEnglish (US)
Pages (from-to)157-174
Number of pages18
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume64
Issue number1
DOIs
StatePublished - Jan 1 2015

Fingerprint

Drop out
Longitudinal Data
Likelihood
Calibration
Weighted Estimating Equations
Observational Study
Generalized Estimating Equations
Alzheimer's Disease
Empirical Likelihood
Longitudinal Study
Small Sample Size
Longitudinal data
Proportion
Inclusion
Simulation Study
Dependent
Demonstrate

Keywords

  • Calibration
  • Dropout
  • Empirical likelihood
  • Longitudinal data

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Pseudoempirical-likelihood-based method using calibration for longitudinal data with dropout. / Chen, Baojiang; Zhou, Xiao Hua; Chan, Gary.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, Vol. 64, No. 1, 01.01.2015, p. 157-174.

Research output: Contribution to journalArticle

@article{dc81f6f9a4f74063a6926798e4fa48ed,
title = "Pseudoempirical-likelihood-based method using calibration for longitudinal data with dropout",
abstract = "In observational studies, interest mainly lies in estimation of the population level relationship between the explanatory variables and dependent variables, and the estimation is often undertaken by using a sample of longitudinal data. In some situations, the longitudinal data sample features biases and loss of estimation efficiency due to non-random dropout. However, inclusion of population level information can increase estimation efficiency. We propose an empirical-likelihood-based method to incorporate population level information in a longitudinal study with dropout. The population level information is incorporated via constraints on functions of the parameters, and non-random dropout bias is corrected by using a weighted generalized estimating equations method. We provide a three-step estimation procedure that makes computation easier. Some commonly used methods are compared in simulation studies, which demonstrate that our proposed method can correct the non-random dropout bias and increase the estimation efficiency, especially for small sample sizes or when the missing proportion is high. In some situations, the improvement in efficiency is substantial. Finally, we apply the method to an Alzheimer's disease study.",
keywords = "Calibration, Dropout, Empirical likelihood, Longitudinal data",
author = "Baojiang Chen and Zhou, {Xiao Hua} and Gary Chan",
year = "2015",
month = "1",
day = "1",
doi = "10.1111/rssc.12063",
language = "English (US)",
volume = "64",
pages = "157--174",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Pseudoempirical-likelihood-based method using calibration for longitudinal data with dropout

AU - Chen, Baojiang

AU - Zhou, Xiao Hua

AU - Chan, Gary

PY - 2015/1/1

Y1 - 2015/1/1

N2 - In observational studies, interest mainly lies in estimation of the population level relationship between the explanatory variables and dependent variables, and the estimation is often undertaken by using a sample of longitudinal data. In some situations, the longitudinal data sample features biases and loss of estimation efficiency due to non-random dropout. However, inclusion of population level information can increase estimation efficiency. We propose an empirical-likelihood-based method to incorporate population level information in a longitudinal study with dropout. The population level information is incorporated via constraints on functions of the parameters, and non-random dropout bias is corrected by using a weighted generalized estimating equations method. We provide a three-step estimation procedure that makes computation easier. Some commonly used methods are compared in simulation studies, which demonstrate that our proposed method can correct the non-random dropout bias and increase the estimation efficiency, especially for small sample sizes or when the missing proportion is high. In some situations, the improvement in efficiency is substantial. Finally, we apply the method to an Alzheimer's disease study.

AB - In observational studies, interest mainly lies in estimation of the population level relationship between the explanatory variables and dependent variables, and the estimation is often undertaken by using a sample of longitudinal data. In some situations, the longitudinal data sample features biases and loss of estimation efficiency due to non-random dropout. However, inclusion of population level information can increase estimation efficiency. We propose an empirical-likelihood-based method to incorporate population level information in a longitudinal study with dropout. The population level information is incorporated via constraints on functions of the parameters, and non-random dropout bias is corrected by using a weighted generalized estimating equations method. We provide a three-step estimation procedure that makes computation easier. Some commonly used methods are compared in simulation studies, which demonstrate that our proposed method can correct the non-random dropout bias and increase the estimation efficiency, especially for small sample sizes or when the missing proportion is high. In some situations, the improvement in efficiency is substantial. Finally, we apply the method to an Alzheimer's disease study.

KW - Calibration

KW - Dropout

KW - Empirical likelihood

KW - Longitudinal data

UR - http://www.scopus.com/inward/record.url?scp=84923194347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84923194347&partnerID=8YFLogxK

U2 - 10.1111/rssc.12063

DO - 10.1111/rssc.12063

M3 - Article

C2 - 25587200

AN - SCOPUS:84923194347

VL - 64

SP - 157

EP - 174

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

IS - 1

ER -