Using multilevel mixtures to evaluate intervention effects in group randomized trials

M. Lee Van Horn, Abigail A. Fagan, Thomas Jaki, Eric C Brown, J. David Hawkins, Michael W. Arthur, Robert D. Abbott, Richard F. Catalano

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

There is evidence to suggest that the effects of behavioral interventions may be limited to specific types of individuals, but methods for evaluating such outcomes have not been fully developed. This study proposes the use of finite mixture models to evaluate whether interventions, and, specifically, group randomized trials, impact participants with certain characteristics or levels of problem behaviors. This study uses latent classes defined by clustering of individuals based on the targeted behaviors and illustrates the model by testing whether a preventive intervention aimed at reducing problem behaviors affects experimental users of illicit substances differently than problematic substance users or those individuals engaged in more serious problem behaviors. An illustrative example is used to demonstrate the identification of latent classes, specification of random effects in a multilevel mixture model, independent validation of latent classes, and the estimation of power for the proposed models to detect intervention effects. This study proposes specific steps for the estimation of multilevel mixture models and their power and suggests that this model can be applied more broadly to understand the effectiveness of interventions.

Original languageEnglish (US)
Pages (from-to)289-326
Number of pages38
JournalMultivariate Behavioral Research
Volume43
Issue number2
DOIs
StatePublished - Apr 2008
Externally publishedYes

Fingerprint

Randomized Trial
Latent Class
Evaluate
Multilevel Models
Mixture Model
Group
Cluster Analysis
Finite Mixture Models
Random Effects
Problem Behavior
Clustering
Model
Specification
Testing
Power (Psychology)
Demonstrate
Behavior Problems
evidence

ASJC Scopus subject areas

  • Mathematics (miscellaneous)
  • Statistics and Probability
  • Social Sciences (miscellaneous)
  • Psychology(all)
  • Experimental and Cognitive Psychology

Cite this

Van Horn, M. L., Fagan, A. A., Jaki, T., Brown, E. C., Hawkins, J. D., Arthur, M. W., ... Catalano, R. F. (2008). Using multilevel mixtures to evaluate intervention effects in group randomized trials. Multivariate Behavioral Research, 43(2), 289-326. https://doi.org/10.1080/00273170802034893

Using multilevel mixtures to evaluate intervention effects in group randomized trials. / Van Horn, M. Lee; Fagan, Abigail A.; Jaki, Thomas; Brown, Eric C; Hawkins, J. David; Arthur, Michael W.; Abbott, Robert D.; Catalano, Richard F.

In: Multivariate Behavioral Research, Vol. 43, No. 2, 04.2008, p. 289-326.

Research output: Contribution to journalArticle

Van Horn, ML, Fagan, AA, Jaki, T, Brown, EC, Hawkins, JD, Arthur, MW, Abbott, RD & Catalano, RF 2008, 'Using multilevel mixtures to evaluate intervention effects in group randomized trials', Multivariate Behavioral Research, vol. 43, no. 2, pp. 289-326. https://doi.org/10.1080/00273170802034893
Van Horn, M. Lee ; Fagan, Abigail A. ; Jaki, Thomas ; Brown, Eric C ; Hawkins, J. David ; Arthur, Michael W. ; Abbott, Robert D. ; Catalano, Richard F. / Using multilevel mixtures to evaluate intervention effects in group randomized trials. In: Multivariate Behavioral Research. 2008 ; Vol. 43, No. 2. pp. 289-326.
@article{b3613c8889354d94ba932662d1a7aab4,
title = "Using multilevel mixtures to evaluate intervention effects in group randomized trials",
abstract = "There is evidence to suggest that the effects of behavioral interventions may be limited to specific types of individuals, but methods for evaluating such outcomes have not been fully developed. This study proposes the use of finite mixture models to evaluate whether interventions, and, specifically, group randomized trials, impact participants with certain characteristics or levels of problem behaviors. This study uses latent classes defined by clustering of individuals based on the targeted behaviors and illustrates the model by testing whether a preventive intervention aimed at reducing problem behaviors affects experimental users of illicit substances differently than problematic substance users or those individuals engaged in more serious problem behaviors. An illustrative example is used to demonstrate the identification of latent classes, specification of random effects in a multilevel mixture model, independent validation of latent classes, and the estimation of power for the proposed models to detect intervention effects. This study proposes specific steps for the estimation of multilevel mixture models and their power and suggests that this model can be applied more broadly to understand the effectiveness of interventions.",
author = "{Van Horn}, {M. Lee} and Fagan, {Abigail A.} and Thomas Jaki and Brown, {Eric C} and Hawkins, {J. David} and Arthur, {Michael W.} and Abbott, {Robert D.} and Catalano, {Richard F.}",
year = "2008",
month = "4",
doi = "10.1080/00273170802034893",
language = "English (US)",
volume = "43",
pages = "289--326",
journal = "Multivariate Behavioral Research",
issn = "0027-3171",
publisher = "Psychology Press Ltd",
number = "2",

}

TY - JOUR

T1 - Using multilevel mixtures to evaluate intervention effects in group randomized trials

AU - Van Horn, M. Lee

AU - Fagan, Abigail A.

AU - Jaki, Thomas

AU - Brown, Eric C

AU - Hawkins, J. David

AU - Arthur, Michael W.

AU - Abbott, Robert D.

AU - Catalano, Richard F.

PY - 2008/4

Y1 - 2008/4

N2 - There is evidence to suggest that the effects of behavioral interventions may be limited to specific types of individuals, but methods for evaluating such outcomes have not been fully developed. This study proposes the use of finite mixture models to evaluate whether interventions, and, specifically, group randomized trials, impact participants with certain characteristics or levels of problem behaviors. This study uses latent classes defined by clustering of individuals based on the targeted behaviors and illustrates the model by testing whether a preventive intervention aimed at reducing problem behaviors affects experimental users of illicit substances differently than problematic substance users or those individuals engaged in more serious problem behaviors. An illustrative example is used to demonstrate the identification of latent classes, specification of random effects in a multilevel mixture model, independent validation of latent classes, and the estimation of power for the proposed models to detect intervention effects. This study proposes specific steps for the estimation of multilevel mixture models and their power and suggests that this model can be applied more broadly to understand the effectiveness of interventions.

AB - There is evidence to suggest that the effects of behavioral interventions may be limited to specific types of individuals, but methods for evaluating such outcomes have not been fully developed. This study proposes the use of finite mixture models to evaluate whether interventions, and, specifically, group randomized trials, impact participants with certain characteristics or levels of problem behaviors. This study uses latent classes defined by clustering of individuals based on the targeted behaviors and illustrates the model by testing whether a preventive intervention aimed at reducing problem behaviors affects experimental users of illicit substances differently than problematic substance users or those individuals engaged in more serious problem behaviors. An illustrative example is used to demonstrate the identification of latent classes, specification of random effects in a multilevel mixture model, independent validation of latent classes, and the estimation of power for the proposed models to detect intervention effects. This study proposes specific steps for the estimation of multilevel mixture models and their power and suggests that this model can be applied more broadly to understand the effectiveness of interventions.

UR - http://www.scopus.com/inward/record.url?scp=45749141698&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=45749141698&partnerID=8YFLogxK

U2 - 10.1080/00273170802034893

DO - 10.1080/00273170802034893

M3 - Article

AN - SCOPUS:45749141698

VL - 43

SP - 289

EP - 326

JO - Multivariate Behavioral Research

JF - Multivariate Behavioral Research

SN - 0027-3171

IS - 2

ER -