Empirical-likelihood-based criteria for model selection on marginal analysis of longitudinal data with dropout missingness

Chixiang Chen, Biyi Shen, Lijun Zhang, Yuan Xue, Ming Wang

Research output: Contribution to journalArticle

Abstract

Longitudinal data are common in clinical trials and observational studies, where missing outcomes due to dropouts are always encountered. Under such context with the assumption of missing at random, the weighted generalized estimating equation (WGEE) approach is widely adopted for marginal analysis. Model selection on marginal mean regression is a crucial aspect of data analysis, and identifying an appropriate correlation structure for model fitting may also be of interest and importance. However, the existing information criteria for model selection in WGEE have limitations, such as separate criteria for the selection of marginal mean and correlation structures, unsatisfactory selection performance in small-sample setups, and so forth. In particular, there are few studies to develop joint information criteria for selection of both marginal mean and correlation structures. In this work, by embedding empirical likelihood into the WGEE framework, we propose two innovative information criteria named a joint empirical Akaike information criterion and a joint empirical Bayesian information criterion, which can simultaneously select the variables for marginal mean regression and also correlation structure. Through extensive simulation studies, these empirical-likelihood-based criteria exhibit robustness, flexibility, and outperformance compared to the other criteria including the weighted quasi-likelihood under the independence model criterion, the missing longitudinal information criterion, and the joint longitudinal information criterion. In addition, we provide a theoretical justification of our proposed criteria, and present two real data examples in practice for further illustration.

Original languageEnglish (US)
Pages (from-to)950-965
Number of pages16
JournalBiometrics
Volume75
Issue number3
DOIs
StatePublished - Sep 1 2019

Fingerprint

dropouts
Information Criterion
Empirical Likelihood
Drop out
Longitudinal Data
Model Selection
Patient Selection
Cost-Benefit Analysis
Correlation Structure
Weighted Estimating Equations
Joints
Generalized Estimating Equations
Regression
selection criteria
Bayesian Information Criterion
Missing at Random
Quasi-likelihood
Observational Study
Akaike Information Criterion
Model Fitting

All Science Journal Classification (ASJC) codes

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

Cite this

@article{d3962f0bdb2b48f7850302d9bdec4dd2,
title = "Empirical-likelihood-based criteria for model selection on marginal analysis of longitudinal data with dropout missingness",
abstract = "Longitudinal data are common in clinical trials and observational studies, where missing outcomes due to dropouts are always encountered. Under such context with the assumption of missing at random, the weighted generalized estimating equation (WGEE) approach is widely adopted for marginal analysis. Model selection on marginal mean regression is a crucial aspect of data analysis, and identifying an appropriate correlation structure for model fitting may also be of interest and importance. However, the existing information criteria for model selection in WGEE have limitations, such as separate criteria for the selection of marginal mean and correlation structures, unsatisfactory selection performance in small-sample setups, and so forth. In particular, there are few studies to develop joint information criteria for selection of both marginal mean and correlation structures. In this work, by embedding empirical likelihood into the WGEE framework, we propose two innovative information criteria named a joint empirical Akaike information criterion and a joint empirical Bayesian information criterion, which can simultaneously select the variables for marginal mean regression and also correlation structure. Through extensive simulation studies, these empirical-likelihood-based criteria exhibit robustness, flexibility, and outperformance compared to the other criteria including the weighted quasi-likelihood under the independence model criterion, the missing longitudinal information criterion, and the joint longitudinal information criterion. In addition, we provide a theoretical justification of our proposed criteria, and present two real data examples in practice for further illustration.",
author = "Chixiang Chen and Biyi Shen and Lijun Zhang and Yuan Xue and Ming Wang",
year = "2019",
month = "9",
day = "1",
doi = "10.1111/biom.13060",
language = "English (US)",
volume = "75",
pages = "950--965",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "3",

}

Empirical-likelihood-based criteria for model selection on marginal analysis of longitudinal data with dropout missingness. / Chen, Chixiang; Shen, Biyi; Zhang, Lijun; Xue, Yuan; Wang, Ming.

In: Biometrics, Vol. 75, No. 3, 01.09.2019, p. 950-965.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Empirical-likelihood-based criteria for model selection on marginal analysis of longitudinal data with dropout missingness

AU - Chen, Chixiang

AU - Shen, Biyi

AU - Zhang, Lijun

AU - Xue, Yuan

AU - Wang, Ming

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Longitudinal data are common in clinical trials and observational studies, where missing outcomes due to dropouts are always encountered. Under such context with the assumption of missing at random, the weighted generalized estimating equation (WGEE) approach is widely adopted for marginal analysis. Model selection on marginal mean regression is a crucial aspect of data analysis, and identifying an appropriate correlation structure for model fitting may also be of interest and importance. However, the existing information criteria for model selection in WGEE have limitations, such as separate criteria for the selection of marginal mean and correlation structures, unsatisfactory selection performance in small-sample setups, and so forth. In particular, there are few studies to develop joint information criteria for selection of both marginal mean and correlation structures. In this work, by embedding empirical likelihood into the WGEE framework, we propose two innovative information criteria named a joint empirical Akaike information criterion and a joint empirical Bayesian information criterion, which can simultaneously select the variables for marginal mean regression and also correlation structure. Through extensive simulation studies, these empirical-likelihood-based criteria exhibit robustness, flexibility, and outperformance compared to the other criteria including the weighted quasi-likelihood under the independence model criterion, the missing longitudinal information criterion, and the joint longitudinal information criterion. In addition, we provide a theoretical justification of our proposed criteria, and present two real data examples in practice for further illustration.

AB - Longitudinal data are common in clinical trials and observational studies, where missing outcomes due to dropouts are always encountered. Under such context with the assumption of missing at random, the weighted generalized estimating equation (WGEE) approach is widely adopted for marginal analysis. Model selection on marginal mean regression is a crucial aspect of data analysis, and identifying an appropriate correlation structure for model fitting may also be of interest and importance. However, the existing information criteria for model selection in WGEE have limitations, such as separate criteria for the selection of marginal mean and correlation structures, unsatisfactory selection performance in small-sample setups, and so forth. In particular, there are few studies to develop joint information criteria for selection of both marginal mean and correlation structures. In this work, by embedding empirical likelihood into the WGEE framework, we propose two innovative information criteria named a joint empirical Akaike information criterion and a joint empirical Bayesian information criterion, which can simultaneously select the variables for marginal mean regression and also correlation structure. Through extensive simulation studies, these empirical-likelihood-based criteria exhibit robustness, flexibility, and outperformance compared to the other criteria including the weighted quasi-likelihood under the independence model criterion, the missing longitudinal information criterion, and the joint longitudinal information criterion. In addition, we provide a theoretical justification of our proposed criteria, and present two real data examples in practice for further illustration.

UR - http://www.scopus.com/inward/record.url?scp=85072056373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072056373&partnerID=8YFLogxK

U2 - 10.1111/biom.13060

DO - 10.1111/biom.13060

M3 - Article

C2 - 31004449

AN - SCOPUS:85072056373

VL - 75

SP - 950

EP - 965

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 3

ER -