An R package for model fitting, model selection and the simulation for longitudinal data with dropout missingness

Cong Xu, Zheng Li, Yuan Xue, Lijun Zhang, Ming Wang

Research output: Contribution to journalArticle

Abstract

Missing data arise frequently in clinical and epidemiological fields, in particular in longitudinal studies. This paper describes the core features of an R package wgeesel, which implements marginal model fitting (i.e., weighted generalized estimating equations, WGEE; doubly robust GEE) for longitudinal data with dropouts under the assumption of missing at random. More importantly, this package comprehensively provide existing information criteria for WGEE model selection on marginal mean or correlation structures. Also, it can serve as a valuable tool for simulating longitudinal data with missing outcomes. Lastly, a real data example and simulations are presented to illustrate and validate our package.

Original languageEnglish (US)
Pages (from-to)2812-2829
Number of pages18
JournalCommunications in Statistics: Simulation and Computation
Volume48
Issue number9
DOIs
StatePublished - Oct 21 2019

Fingerprint

Drop out
Model Fitting
Longitudinal Data
Model Selection
Weighted Estimating Equations
Marginal Model
Missing at Random
Generalized Estimating Equations
Information Criterion
Longitudinal Study
Correlation Structure
Missing Data
Simulation

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modeling and Simulation

Cite this

@article{4b20abd8a3584a2987f33fb0ec486830,
title = "An R package for model fitting, model selection and the simulation for longitudinal data with dropout missingness",
abstract = "Missing data arise frequently in clinical and epidemiological fields, in particular in longitudinal studies. This paper describes the core features of an R package wgeesel, which implements marginal model fitting (i.e., weighted generalized estimating equations, WGEE; doubly robust GEE) for longitudinal data with dropouts under the assumption of missing at random. More importantly, this package comprehensively provide existing information criteria for WGEE model selection on marginal mean or correlation structures. Also, it can serve as a valuable tool for simulating longitudinal data with missing outcomes. Lastly, a real data example and simulations are presented to illustrate and validate our package.",
author = "Cong Xu and Zheng Li and Yuan Xue and Lijun Zhang and Ming Wang",
year = "2019",
month = "10",
day = "21",
doi = "10.1080/03610918.2018.1468457",
language = "English (US)",
volume = "48",
pages = "2812--2829",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "9",

}

An R package for model fitting, model selection and the simulation for longitudinal data with dropout missingness. / Xu, Cong; Li, Zheng; Xue, Yuan; Zhang, Lijun; Wang, Ming.

In: Communications in Statistics: Simulation and Computation, Vol. 48, No. 9, 21.10.2019, p. 2812-2829.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An R package for model fitting, model selection and the simulation for longitudinal data with dropout missingness

AU - Xu, Cong

AU - Li, Zheng

AU - Xue, Yuan

AU - Zhang, Lijun

AU - Wang, Ming

PY - 2019/10/21

Y1 - 2019/10/21

N2 - Missing data arise frequently in clinical and epidemiological fields, in particular in longitudinal studies. This paper describes the core features of an R package wgeesel, which implements marginal model fitting (i.e., weighted generalized estimating equations, WGEE; doubly robust GEE) for longitudinal data with dropouts under the assumption of missing at random. More importantly, this package comprehensively provide existing information criteria for WGEE model selection on marginal mean or correlation structures. Also, it can serve as a valuable tool for simulating longitudinal data with missing outcomes. Lastly, a real data example and simulations are presented to illustrate and validate our package.

AB - Missing data arise frequently in clinical and epidemiological fields, in particular in longitudinal studies. This paper describes the core features of an R package wgeesel, which implements marginal model fitting (i.e., weighted generalized estimating equations, WGEE; doubly robust GEE) for longitudinal data with dropouts under the assumption of missing at random. More importantly, this package comprehensively provide existing information criteria for WGEE model selection on marginal mean or correlation structures. Also, it can serve as a valuable tool for simulating longitudinal data with missing outcomes. Lastly, a real data example and simulations are presented to illustrate and validate our package.

UR - http://www.scopus.com/inward/record.url?scp=85055273502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055273502&partnerID=8YFLogxK

U2 - 10.1080/03610918.2018.1468457

DO - 10.1080/03610918.2018.1468457

M3 - Article

AN - SCOPUS:85055273502

VL - 48

SP - 2812

EP - 2829

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 9

ER -