Using Fit Indexes to Select a Covariance Model for Longitudinal Data

Siwei Liu, Michael J. Rovine, Peter C.M. Molenaar

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This study investigated the performance of fit indexes in selecting a covariance structure for longitudinal data. Data were simulated to follow a compound symmetry, first-order autoregressive, first-order moving average, or random-coefficients covariance structure. We examined the ability of the likelihood ratio test (LRT), root mean square error of approximation (RMSEA), comparative fit index (CFI), and Tucker-Lewis Index (TLI) to reject misspecified models with varying degrees of misspecification. With a sample size of 20, RMSEA, CFI, and TLI are high in both Type I and Type II error rates, whereas LRT has a high Type II error rate. With a sample size of 100, these indexes generally have satisfactory performance, but CFI and TLI are affected by a confounding effect of their baseline model. Akaike's Information Criterion (AIC) and Bayesian Information Criterion (BIC) have high success rates in identifying the true model when sample size is 100. A comparison with the mixed model approach indicates that separately modeling the means and covariance structures in structural equation modeling dramatically improves the success rate of AIC and BIC.

Original languageEnglish (US)
Pages (from-to)633-650
Number of pages18
JournalStructural Equation Modeling
Volume19
Issue number4
DOIs
StatePublished - Oct 1 2012

Fingerprint

Longitudinal Data
Mean square error
Covariance Structure
Type II error
Bayesian Information Criterion
Sample Size
Akaike Information Criterion
Likelihood Ratio Test
Model
Error Rate
Compound Symmetry
Roots
Misspecified Model
First-order
Structural Equation Modeling
Random Coefficients
Longitudinal data
Confounding
Misspecification
Moving Average

All Science Journal Classification (ASJC) codes

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

Cite this

@article{4fa84a8aab734a3e8d99c67c351b6975,
title = "Using Fit Indexes to Select a Covariance Model for Longitudinal Data",
abstract = "This study investigated the performance of fit indexes in selecting a covariance structure for longitudinal data. Data were simulated to follow a compound symmetry, first-order autoregressive, first-order moving average, or random-coefficients covariance structure. We examined the ability of the likelihood ratio test (LRT), root mean square error of approximation (RMSEA), comparative fit index (CFI), and Tucker-Lewis Index (TLI) to reject misspecified models with varying degrees of misspecification. With a sample size of 20, RMSEA, CFI, and TLI are high in both Type I and Type II error rates, whereas LRT has a high Type II error rate. With a sample size of 100, these indexes generally have satisfactory performance, but CFI and TLI are affected by a confounding effect of their baseline model. Akaike's Information Criterion (AIC) and Bayesian Information Criterion (BIC) have high success rates in identifying the true model when sample size is 100. A comparison with the mixed model approach indicates that separately modeling the means and covariance structures in structural equation modeling dramatically improves the success rate of AIC and BIC.",
author = "Siwei Liu and Rovine, {Michael J.} and Molenaar, {Peter C.M.}",
year = "2012",
month = "10",
day = "1",
doi = "10.1080/10705511.2012.726918",
language = "English (US)",
volume = "19",
pages = "633--650",
journal = "Structural Equation Modeling",
issn = "1070-5511",
publisher = "Psychology Press Ltd",
number = "4",

}

Using Fit Indexes to Select a Covariance Model for Longitudinal Data. / Liu, Siwei; Rovine, Michael J.; Molenaar, Peter C.M.

In: Structural Equation Modeling, Vol. 19, No. 4, 01.10.2012, p. 633-650.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using Fit Indexes to Select a Covariance Model for Longitudinal Data

AU - Liu, Siwei

AU - Rovine, Michael J.

AU - Molenaar, Peter C.M.

PY - 2012/10/1

Y1 - 2012/10/1

N2 - This study investigated the performance of fit indexes in selecting a covariance structure for longitudinal data. Data were simulated to follow a compound symmetry, first-order autoregressive, first-order moving average, or random-coefficients covariance structure. We examined the ability of the likelihood ratio test (LRT), root mean square error of approximation (RMSEA), comparative fit index (CFI), and Tucker-Lewis Index (TLI) to reject misspecified models with varying degrees of misspecification. With a sample size of 20, RMSEA, CFI, and TLI are high in both Type I and Type II error rates, whereas LRT has a high Type II error rate. With a sample size of 100, these indexes generally have satisfactory performance, but CFI and TLI are affected by a confounding effect of their baseline model. Akaike's Information Criterion (AIC) and Bayesian Information Criterion (BIC) have high success rates in identifying the true model when sample size is 100. A comparison with the mixed model approach indicates that separately modeling the means and covariance structures in structural equation modeling dramatically improves the success rate of AIC and BIC.

AB - This study investigated the performance of fit indexes in selecting a covariance structure for longitudinal data. Data were simulated to follow a compound symmetry, first-order autoregressive, first-order moving average, or random-coefficients covariance structure. We examined the ability of the likelihood ratio test (LRT), root mean square error of approximation (RMSEA), comparative fit index (CFI), and Tucker-Lewis Index (TLI) to reject misspecified models with varying degrees of misspecification. With a sample size of 20, RMSEA, CFI, and TLI are high in both Type I and Type II error rates, whereas LRT has a high Type II error rate. With a sample size of 100, these indexes generally have satisfactory performance, but CFI and TLI are affected by a confounding effect of their baseline model. Akaike's Information Criterion (AIC) and Bayesian Information Criterion (BIC) have high success rates in identifying the true model when sample size is 100. A comparison with the mixed model approach indicates that separately modeling the means and covariance structures in structural equation modeling dramatically improves the success rate of AIC and BIC.

UR - http://www.scopus.com/inward/record.url?scp=84868277466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868277466&partnerID=8YFLogxK

U2 - 10.1080/10705511.2012.726918

DO - 10.1080/10705511.2012.726918

M3 - Article

AN - SCOPUS:84868277466

VL - 19

SP - 633

EP - 650

JO - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

IS - 4

ER -