Many-Level Multilevel Structural Equation Modeling: An Efficient Evaluation Strategy

Joshua N. Pritikin, Michael D. Hunter, Timo von Oertzen, Timothy R. Brick, Steven M. Boker

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Structural equation models are increasingly used for clustered or multilevel data in cases where mixed regression is too inflexible. However, when there are many levels of nesting, these models can become difficult to estimate. We introduce a novel evaluation strategy, Rampart, that applies an orthogonal rotation to the parts of a model that conform to commonly met requirements. This rotation dramatically simplifies fit evaluation in a way that becomes more potent as the size of the data set increases. We validate and evaluate the implementation using a 3-level latent regression simulation study. Then we analyze data from a statewide child behavioral health measure administered by the Oklahoma Department of Human Services. We demonstrate the efficiency of Rampart compared to other similar software using a latent factor model with a 5-level decomposition of latent variance. Rampart is implemented in OpenMx, a free and open source software package.

Original languageEnglish (US)
Pages (from-to)684-698
Number of pages15
JournalStructural Equation Modeling
Volume24
Issue number5
DOIs
StatePublished - Sep 3 2017

Fingerprint

Structural Equation Modeling
Evaluation
Regression
evaluation
regression
Structural Equation Model
Open Source Software
Factor Models
structural model
Software Package
Simplify
Health
Simulation Study
Software packages
Decompose
efficiency
simulation
Software
Evaluate
Requirements

All Science Journal Classification (ASJC) codes

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

Cite this

Pritikin, Joshua N. ; Hunter, Michael D. ; von Oertzen, Timo ; Brick, Timothy R. ; Boker, Steven M. / Many-Level Multilevel Structural Equation Modeling : An Efficient Evaluation Strategy. In: Structural Equation Modeling. 2017 ; Vol. 24, No. 5. pp. 684-698.
@article{04cca4af67c0461180c7a8deaf0a1045,
title = "Many-Level Multilevel Structural Equation Modeling: An Efficient Evaluation Strategy",
abstract = "Structural equation models are increasingly used for clustered or multilevel data in cases where mixed regression is too inflexible. However, when there are many levels of nesting, these models can become difficult to estimate. We introduce a novel evaluation strategy, Rampart, that applies an orthogonal rotation to the parts of a model that conform to commonly met requirements. This rotation dramatically simplifies fit evaluation in a way that becomes more potent as the size of the data set increases. We validate and evaluate the implementation using a 3-level latent regression simulation study. Then we analyze data from a statewide child behavioral health measure administered by the Oklahoma Department of Human Services. We demonstrate the efficiency of Rampart compared to other similar software using a latent factor model with a 5-level decomposition of latent variance. Rampart is implemented in OpenMx, a free and open source software package.",
author = "Pritikin, {Joshua N.} and Hunter, {Michael D.} and {von Oertzen}, Timo and Brick, {Timothy R.} and Boker, {Steven M.}",
year = "2017",
month = "9",
day = "3",
doi = "10.1080/10705511.2017.1293542",
language = "English (US)",
volume = "24",
pages = "684--698",
journal = "Structural Equation Modeling",
issn = "1070-5511",
publisher = "Psychology Press Ltd",
number = "5",

}

Many-Level Multilevel Structural Equation Modeling : An Efficient Evaluation Strategy. / Pritikin, Joshua N.; Hunter, Michael D.; von Oertzen, Timo; Brick, Timothy R.; Boker, Steven M.

In: Structural Equation Modeling, Vol. 24, No. 5, 03.09.2017, p. 684-698.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Many-Level Multilevel Structural Equation Modeling

T2 - An Efficient Evaluation Strategy

AU - Pritikin, Joshua N.

AU - Hunter, Michael D.

AU - von Oertzen, Timo

AU - Brick, Timothy R.

AU - Boker, Steven M.

PY - 2017/9/3

Y1 - 2017/9/3

N2 - Structural equation models are increasingly used for clustered or multilevel data in cases where mixed regression is too inflexible. However, when there are many levels of nesting, these models can become difficult to estimate. We introduce a novel evaluation strategy, Rampart, that applies an orthogonal rotation to the parts of a model that conform to commonly met requirements. This rotation dramatically simplifies fit evaluation in a way that becomes more potent as the size of the data set increases. We validate and evaluate the implementation using a 3-level latent regression simulation study. Then we analyze data from a statewide child behavioral health measure administered by the Oklahoma Department of Human Services. We demonstrate the efficiency of Rampart compared to other similar software using a latent factor model with a 5-level decomposition of latent variance. Rampart is implemented in OpenMx, a free and open source software package.

AB - Structural equation models are increasingly used for clustered or multilevel data in cases where mixed regression is too inflexible. However, when there are many levels of nesting, these models can become difficult to estimate. We introduce a novel evaluation strategy, Rampart, that applies an orthogonal rotation to the parts of a model that conform to commonly met requirements. This rotation dramatically simplifies fit evaluation in a way that becomes more potent as the size of the data set increases. We validate and evaluate the implementation using a 3-level latent regression simulation study. Then we analyze data from a statewide child behavioral health measure administered by the Oklahoma Department of Human Services. We demonstrate the efficiency of Rampart compared to other similar software using a latent factor model with a 5-level decomposition of latent variance. Rampart is implemented in OpenMx, a free and open source software package.

UR - http://www.scopus.com/inward/record.url?scp=85016108129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016108129&partnerID=8YFLogxK

U2 - 10.1080/10705511.2017.1293542

DO - 10.1080/10705511.2017.1293542

M3 - Article

C2 - 29606847

AN - SCOPUS:85016108129

VL - 24

SP - 684

EP - 698

JO - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

IS - 5

ER -