A Comparison of Methods for Uncovering Sample Heterogeneity: Structural Equation Model Trees and Finite Mixture Models

Ross Jacobucci, Kevin Grimm, John J. McArdle

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Although finite mixture models have received considerable attention, particularly in the social and behavioral sciences, an alternative method for creating homogeneous groups, structural equation model trees (Brandmaier, von Oertzen, McArdle, & Lindenberger, 2013), is a recent development that has received much less application and consideration. It is our aim to compare and contrast these methods for uncovering sample heterogeneity. We illustrate the use of these methods with longitudinal reading achievement data collected as part of the Early Childhood Longitudinal Study–Kindergarten Cohort. We present the use of structural equation model trees as an alternative framework that does not assume the classes are latent and uses observed covariates to derive their structure. We consider these methods as complementary and discuss their respective strengths and limitations for creating homogeneous groups.

Original languageEnglish (US)
Pages (from-to)1-13
Number of pages13
JournalStructural Equation Modeling
DOIs
StateAccepted/In press - Dec 8 2016

Fingerprint

comparison of methods
Finite Mixture Models
Structural Equation Model
structural model
Homogeneous Groups
behavioral science
Alternatives
Covariates
Group
social science
childhood
Structural equation model
Finite mixture models

Keywords

  • decision trees
  • finite mixture models
  • growth mixture models
  • structural equation model trees

ASJC Scopus subject areas

  • Decision Sciences(all)
  • Modeling and Simulation
  • Sociology and Political Science
  • Economics, Econometrics and Finance(all)

Cite this

A Comparison of Methods for Uncovering Sample Heterogeneity : Structural Equation Model Trees and Finite Mixture Models. / Jacobucci, Ross; Grimm, Kevin; McArdle, John J.

In: Structural Equation Modeling, 08.12.2016, p. 1-13.

Research output: Contribution to journalArticle

@article{b4a39b2c6d8d4d68a4adc73c62e652d2,
title = "A Comparison of Methods for Uncovering Sample Heterogeneity: Structural Equation Model Trees and Finite Mixture Models",
abstract = "Although finite mixture models have received considerable attention, particularly in the social and behavioral sciences, an alternative method for creating homogeneous groups, structural equation model trees (Brandmaier, von Oertzen, McArdle, & Lindenberger, 2013), is a recent development that has received much less application and consideration. It is our aim to compare and contrast these methods for uncovering sample heterogeneity. We illustrate the use of these methods with longitudinal reading achievement data collected as part of the Early Childhood Longitudinal Study–Kindergarten Cohort. We present the use of structural equation model trees as an alternative framework that does not assume the classes are latent and uses observed covariates to derive their structure. We consider these methods as complementary and discuss their respective strengths and limitations for creating homogeneous groups.",
keywords = "decision trees, finite mixture models, growth mixture models, structural equation model trees",
author = "Ross Jacobucci and Kevin Grimm and McArdle, {John J.}",
year = "2016",
month = "12",
day = "8",
doi = "10.1080/10705511.2016.1250637",
language = "English (US)",
pages = "1--13",
journal = "Structural Equation Modeling",
issn = "1070-5511",
publisher = "Psychology Press Ltd",

}

TY - JOUR

T1 - A Comparison of Methods for Uncovering Sample Heterogeneity

T2 - Structural Equation Model Trees and Finite Mixture Models

AU - Jacobucci, Ross

AU - Grimm, Kevin

AU - McArdle, John J.

PY - 2016/12/8

Y1 - 2016/12/8

N2 - Although finite mixture models have received considerable attention, particularly in the social and behavioral sciences, an alternative method for creating homogeneous groups, structural equation model trees (Brandmaier, von Oertzen, McArdle, & Lindenberger, 2013), is a recent development that has received much less application and consideration. It is our aim to compare and contrast these methods for uncovering sample heterogeneity. We illustrate the use of these methods with longitudinal reading achievement data collected as part of the Early Childhood Longitudinal Study–Kindergarten Cohort. We present the use of structural equation model trees as an alternative framework that does not assume the classes are latent and uses observed covariates to derive their structure. We consider these methods as complementary and discuss their respective strengths and limitations for creating homogeneous groups.

AB - Although finite mixture models have received considerable attention, particularly in the social and behavioral sciences, an alternative method for creating homogeneous groups, structural equation model trees (Brandmaier, von Oertzen, McArdle, & Lindenberger, 2013), is a recent development that has received much less application and consideration. It is our aim to compare and contrast these methods for uncovering sample heterogeneity. We illustrate the use of these methods with longitudinal reading achievement data collected as part of the Early Childhood Longitudinal Study–Kindergarten Cohort. We present the use of structural equation model trees as an alternative framework that does not assume the classes are latent and uses observed covariates to derive their structure. We consider these methods as complementary and discuss their respective strengths and limitations for creating homogeneous groups.

KW - decision trees

KW - finite mixture models

KW - growth mixture models

KW - structural equation model trees

UR - http://www.scopus.com/inward/record.url?scp=85002251495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002251495&partnerID=8YFLogxK

U2 - 10.1080/10705511.2016.1250637

DO - 10.1080/10705511.2016.1250637

M3 - Article

AN - SCOPUS:85002251495

SP - 1

EP - 13

JO - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

ER -