Estimating functions for evaluating treatment effects in cluster-randomized longitudinal studies in the presence of drop-out and non-compliance

Grace Y. Yi, Richard J. Cook, Chen Baojiang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We describe methods for analyzing longitudinal binary data from cluster-randomized trials in which responses are incompletelyobserved and subjects maynot be fullycompliant with the prescribed treatment regimen. The method is based on a marginal regression model for the response where parameter estimates are obtained from generalized estimating equations. Estimating equations are also employed to estimate parameters of the missing data process which are used to compute inverse probabilityweights. A model is specified for the compliance process which facilitates estimating the expectation of the contributions to the estimating function for the response parameters among individuals without compliance data, which occurs when the control treatment involves no intervention. The approach is robust in the sense that semiparametric models are used for the response and the missing data processes and robust variance estimates are advocated. The proposed method is shown to perform well in simulation studies, and data from a randomized trial of patients with depression are analyzed for illustration.

Original languageEnglish (US)
Pages (from-to)232-255
Number of pages24
JournalCanadian Journal of Statistics
Volume38
Issue number2
DOIs
StatePublished - Jun 1 2010

Fingerprint

Noncompliance
Estimating Function
Drop out
Longitudinal Study
Treatment Effects
Randomized Trial
Missing Data
Compliance
Estimate
Marginal Model
Generalized Estimating Equations
Estimating Equation
Binary Data
Semiparametric Model
Longitudinal Data
Regression Model
Simulation Study
Treatment effects
Longitudinal study
Missing data

Keywords

  • Compliance
  • Estimating function
  • Longitudinal data
  • Treatment efficacy

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Estimating functions for evaluating treatment effects in cluster-randomized longitudinal studies in the presence of drop-out and non-compliance. / Yi, Grace Y.; Cook, Richard J.; Baojiang, Chen.

In: Canadian Journal of Statistics, Vol. 38, No. 2, 01.06.2010, p. 232-255.

Research output: Contribution to journalArticle

@article{db9b600614464e338025301587dbc9fc,
title = "Estimating functions for evaluating treatment effects in cluster-randomized longitudinal studies in the presence of drop-out and non-compliance",
abstract = "We describe methods for analyzing longitudinal binary data from cluster-randomized trials in which responses are incompletelyobserved and subjects maynot be fullycompliant with the prescribed treatment regimen. The method is based on a marginal regression model for the response where parameter estimates are obtained from generalized estimating equations. Estimating equations are also employed to estimate parameters of the missing data process which are used to compute inverse probabilityweights. A model is specified for the compliance process which facilitates estimating the expectation of the contributions to the estimating function for the response parameters among individuals without compliance data, which occurs when the control treatment involves no intervention. The approach is robust in the sense that semiparametric models are used for the response and the missing data processes and robust variance estimates are advocated. The proposed method is shown to perform well in simulation studies, and data from a randomized trial of patients with depression are analyzed for illustration.",
keywords = "Compliance, Estimating function, Longitudinal data, Treatment efficacy",
author = "Yi, {Grace Y.} and Cook, {Richard J.} and Chen Baojiang",
year = "2010",
month = "6",
day = "1",
doi = "10.1002/cjs.10058",
language = "English (US)",
volume = "38",
pages = "232--255",
journal = "Canadian Journal of Statistics",
issn = "0319-5724",
publisher = "Statistical Society of Canada",
number = "2",

}

TY - JOUR

T1 - Estimating functions for evaluating treatment effects in cluster-randomized longitudinal studies in the presence of drop-out and non-compliance

AU - Yi, Grace Y.

AU - Cook, Richard J.

AU - Baojiang, Chen

PY - 2010/6/1

Y1 - 2010/6/1

N2 - We describe methods for analyzing longitudinal binary data from cluster-randomized trials in which responses are incompletelyobserved and subjects maynot be fullycompliant with the prescribed treatment regimen. The method is based on a marginal regression model for the response where parameter estimates are obtained from generalized estimating equations. Estimating equations are also employed to estimate parameters of the missing data process which are used to compute inverse probabilityweights. A model is specified for the compliance process which facilitates estimating the expectation of the contributions to the estimating function for the response parameters among individuals without compliance data, which occurs when the control treatment involves no intervention. The approach is robust in the sense that semiparametric models are used for the response and the missing data processes and robust variance estimates are advocated. The proposed method is shown to perform well in simulation studies, and data from a randomized trial of patients with depression are analyzed for illustration.

AB - We describe methods for analyzing longitudinal binary data from cluster-randomized trials in which responses are incompletelyobserved and subjects maynot be fullycompliant with the prescribed treatment regimen. The method is based on a marginal regression model for the response where parameter estimates are obtained from generalized estimating equations. Estimating equations are also employed to estimate parameters of the missing data process which are used to compute inverse probabilityweights. A model is specified for the compliance process which facilitates estimating the expectation of the contributions to the estimating function for the response parameters among individuals without compliance data, which occurs when the control treatment involves no intervention. The approach is robust in the sense that semiparametric models are used for the response and the missing data processes and robust variance estimates are advocated. The proposed method is shown to perform well in simulation studies, and data from a randomized trial of patients with depression are analyzed for illustration.

KW - Compliance

KW - Estimating function

KW - Longitudinal data

KW - Treatment efficacy

UR - http://www.scopus.com/inward/record.url?scp=77955118534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955118534&partnerID=8YFLogxK

U2 - 10.1002/cjs.10058

DO - 10.1002/cjs.10058

M3 - Article

AN - SCOPUS:77955118534

VL - 38

SP - 232

EP - 255

JO - Canadian Journal of Statistics

JF - Canadian Journal of Statistics

SN - 0319-5724

IS - 2

ER -