Cluster Randomized Trials With Treatment Noncompliance

Booil Jo, Tihomir Asparouhov, Bengt O. Muthén, Nicholas S Ialongo, C. Hendricks Brown

Research output: Contribution to journalArticle

Abstract

Cluster randomized trials (CRTs) have been widely used in field experiments treating a cluster of individuals as the unit of randomization. This study focused particularly on situations where CRTs are accompanied by a common complication, namely, treatment noncompliance or, more generally, intervention nonadherence. In CRTs, compliance may be related not only to individual characteristics but also to the environment of clusters individuals belong to. Therefore, analyses ignoring the connection between compliance and clustering may not provide valid results. Although randomized field experiments often suffer from both noncompliance and clustering of the data, these features have been studied as separate rather than concurrent problems. On the basis of Monte Carlo simulations, this study demonstrated how clustering and noncompliance may affect statistical inferences and how these two complications can be accounted for simultaneously. In particular, the effect of the intervention on individuals who not only were assigned to active intervention but also abided by this intervention assignment (complier average causal effect) was the focus. For estimation of intervention effects considering noncompliance and data clustering, an ML-EM estimation method was employed.

Original languageEnglish (US)
Pages (from-to)1-18
Number of pages18
JournalPsychological Methods
Volume13
Issue number1
DOIs
StatePublished - Mar 2008

Fingerprint

Cluster Analysis
Compliance
Random Allocation

Keywords

  • cluster randomized trial
  • compliance intraclass correlation
  • complier average causal effect
  • ML-EM estimation
  • treatment noncompliance

ASJC Scopus subject areas

  • Psychology(all)

Cite this

Cluster Randomized Trials With Treatment Noncompliance. / Jo, Booil; Asparouhov, Tihomir; Muthén, Bengt O.; Ialongo, Nicholas S; Brown, C. Hendricks.

In: Psychological Methods, Vol. 13, No. 1, 03.2008, p. 1-18.

Research output: Contribution to journalArticle

Jo, Booil ; Asparouhov, Tihomir ; Muthén, Bengt O. ; Ialongo, Nicholas S ; Brown, C. Hendricks. / Cluster Randomized Trials With Treatment Noncompliance. In: Psychological Methods. 2008 ; Vol. 13, No. 1. pp. 1-18.
@article{25b7195e023f4845bfc44aea0bfbae75,
title = "Cluster Randomized Trials With Treatment Noncompliance",
abstract = "Cluster randomized trials (CRTs) have been widely used in field experiments treating a cluster of individuals as the unit of randomization. This study focused particularly on situations where CRTs are accompanied by a common complication, namely, treatment noncompliance or, more generally, intervention nonadherence. In CRTs, compliance may be related not only to individual characteristics but also to the environment of clusters individuals belong to. Therefore, analyses ignoring the connection between compliance and clustering may not provide valid results. Although randomized field experiments often suffer from both noncompliance and clustering of the data, these features have been studied as separate rather than concurrent problems. On the basis of Monte Carlo simulations, this study demonstrated how clustering and noncompliance may affect statistical inferences and how these two complications can be accounted for simultaneously. In particular, the effect of the intervention on individuals who not only were assigned to active intervention but also abided by this intervention assignment (complier average causal effect) was the focus. For estimation of intervention effects considering noncompliance and data clustering, an ML-EM estimation method was employed.",
keywords = "cluster randomized trial, compliance intraclass correlation, complier average causal effect, ML-EM estimation, treatment noncompliance",
author = "Booil Jo and Tihomir Asparouhov and Muth{\'e}n, {Bengt O.} and Ialongo, {Nicholas S} and Brown, {C. Hendricks}",
year = "2008",
month = "3",
doi = "10.1037/1082-989X.13.1.1",
language = "English (US)",
volume = "13",
pages = "1--18",
journal = "Psychological Methods",
issn = "1082-989X",
publisher = "American Psychological Association Inc.",
number = "1",

}

TY - JOUR

T1 - Cluster Randomized Trials With Treatment Noncompliance

AU - Jo, Booil

AU - Asparouhov, Tihomir

AU - Muthén, Bengt O.

AU - Ialongo, Nicholas S

AU - Brown, C. Hendricks

PY - 2008/3

Y1 - 2008/3

N2 - Cluster randomized trials (CRTs) have been widely used in field experiments treating a cluster of individuals as the unit of randomization. This study focused particularly on situations where CRTs are accompanied by a common complication, namely, treatment noncompliance or, more generally, intervention nonadherence. In CRTs, compliance may be related not only to individual characteristics but also to the environment of clusters individuals belong to. Therefore, analyses ignoring the connection between compliance and clustering may not provide valid results. Although randomized field experiments often suffer from both noncompliance and clustering of the data, these features have been studied as separate rather than concurrent problems. On the basis of Monte Carlo simulations, this study demonstrated how clustering and noncompliance may affect statistical inferences and how these two complications can be accounted for simultaneously. In particular, the effect of the intervention on individuals who not only were assigned to active intervention but also abided by this intervention assignment (complier average causal effect) was the focus. For estimation of intervention effects considering noncompliance and data clustering, an ML-EM estimation method was employed.

AB - Cluster randomized trials (CRTs) have been widely used in field experiments treating a cluster of individuals as the unit of randomization. This study focused particularly on situations where CRTs are accompanied by a common complication, namely, treatment noncompliance or, more generally, intervention nonadherence. In CRTs, compliance may be related not only to individual characteristics but also to the environment of clusters individuals belong to. Therefore, analyses ignoring the connection between compliance and clustering may not provide valid results. Although randomized field experiments often suffer from both noncompliance and clustering of the data, these features have been studied as separate rather than concurrent problems. On the basis of Monte Carlo simulations, this study demonstrated how clustering and noncompliance may affect statistical inferences and how these two complications can be accounted for simultaneously. In particular, the effect of the intervention on individuals who not only were assigned to active intervention but also abided by this intervention assignment (complier average causal effect) was the focus. For estimation of intervention effects considering noncompliance and data clustering, an ML-EM estimation method was employed.

KW - cluster randomized trial

KW - compliance intraclass correlation

KW - complier average causal effect

KW - ML-EM estimation

KW - treatment noncompliance

UR - http://www.scopus.com/inward/record.url?scp=43049104651&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43049104651&partnerID=8YFLogxK

U2 - 10.1037/1082-989X.13.1.1

DO - 10.1037/1082-989X.13.1.1

M3 - Article

VL - 13

SP - 1

EP - 18

JO - Psychological Methods

JF - Psychological Methods

SN - 1082-989X

IS - 1

ER -