Using Structural Equation Modeling to Assess Functional Connectivity in the Brain

Power and Sample Size Considerations

Georgios Sideridis, Panagiotis Simos, Andrew Papanicolaou, Jack Fletcher

Research output: Contribution to journalArticle

74 Citations (Scopus)

Abstract

The present study assessed the impact of sample size on the power and fit of structural equation modeling applied to functional brain connectivity hypotheses. The data consisted of time-constrained minimum norm estimates of regional brain activity during performance of a reading task obtained with magnetoencephalography. Power analysis was first conducted for an autoregressive model with 5 latent variables (brain regions), each defined by 3 indicators (successive activity time bins). A series of simulations were then run by generating data from an existing pool of 51 typical readers (aged 7.5-12.5 years). Sample sizes ranged between 20 and 1,000 participants and for each sample size 1,000 replications were run. Results were evaluated using chi-square Type I errors, model convergence, mean RMSEA (root mean square error of approximation) values, confidence intervals of the RMSEA, structural path stability, and Δ-Fit index values. Results suggested that 70 to 80 participants were adequate to model relationships reflecting close to not so close fit as per MacCallum et al.'s recommendations. Sample sizes of 50 participants were associated with satisfactory fit. It is concluded that structural equation modeling is a viable methodology to model complex regional interdependencies in brain activation in pediatric populations.

Original languageEnglish (US)
Pages (from-to)733-758
Number of pages26
JournalEducational and Psychological Measurement
Volume74
Issue number5
DOIs
StatePublished - Jan 1 2014

Fingerprint

Structural Equation Modeling
Sample Size
Brain
brain
Connectivity
Mean square error
Magnetoencephalography
Roots
Mean Convergence
Pediatrics
Power Analysis
Interdependencies
Error Model
Chi-square
Type I error
Bins
Latent Variables
Autoregressive Model
Approximation
activation

All Science Journal Classification (ASJC) codes

  • Education
  • Developmental and Educational Psychology
  • Applied Psychology
  • Applied Mathematics

Cite this

Using Structural Equation Modeling to Assess Functional Connectivity in the Brain : Power and Sample Size Considerations. / Sideridis, Georgios; Simos, Panagiotis; Papanicolaou, Andrew; Fletcher, Jack.

In: Educational and Psychological Measurement, Vol. 74, No. 5, 01.01.2014, p. 733-758.

Research output: Contribution to journalArticle

Sideridis, Georgios ; Simos, Panagiotis ; Papanicolaou, Andrew ; Fletcher, Jack. / Using Structural Equation Modeling to Assess Functional Connectivity in the Brain : Power and Sample Size Considerations. In: Educational and Psychological Measurement. 2014 ; Vol. 74, No. 5. pp. 733-758.
@article{92d41cd57869497597eec6db5e56d33f,
title = "Using Structural Equation Modeling to Assess Functional Connectivity in the Brain: Power and Sample Size Considerations",
abstract = "The present study assessed the impact of sample size on the power and fit of structural equation modeling applied to functional brain connectivity hypotheses. The data consisted of time-constrained minimum norm estimates of regional brain activity during performance of a reading task obtained with magnetoencephalography. Power analysis was first conducted for an autoregressive model with 5 latent variables (brain regions), each defined by 3 indicators (successive activity time bins). A series of simulations were then run by generating data from an existing pool of 51 typical readers (aged 7.5-12.5 years). Sample sizes ranged between 20 and 1,000 participants and for each sample size 1,000 replications were run. Results were evaluated using chi-square Type I errors, model convergence, mean RMSEA (root mean square error of approximation) values, confidence intervals of the RMSEA, structural path stability, and Δ-Fit index values. Results suggested that 70 to 80 participants were adequate to model relationships reflecting close to not so close fit as per MacCallum et al.'s recommendations. Sample sizes of 50 participants were associated with satisfactory fit. It is concluded that structural equation modeling is a viable methodology to model complex regional interdependencies in brain activation in pediatric populations.",
author = "Georgios Sideridis and Panagiotis Simos and Andrew Papanicolaou and Jack Fletcher",
year = "2014",
month = "1",
day = "1",
doi = "10.1177/0013164414525397",
language = "English (US)",
volume = "74",
pages = "733--758",
journal = "Educational and Psychological Measurement",
issn = "0013-1644",
publisher = "SAGE Publications Inc.",
number = "5",

}

TY - JOUR

T1 - Using Structural Equation Modeling to Assess Functional Connectivity in the Brain

T2 - Power and Sample Size Considerations

AU - Sideridis, Georgios

AU - Simos, Panagiotis

AU - Papanicolaou, Andrew

AU - Fletcher, Jack

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The present study assessed the impact of sample size on the power and fit of structural equation modeling applied to functional brain connectivity hypotheses. The data consisted of time-constrained minimum norm estimates of regional brain activity during performance of a reading task obtained with magnetoencephalography. Power analysis was first conducted for an autoregressive model with 5 latent variables (brain regions), each defined by 3 indicators (successive activity time bins). A series of simulations were then run by generating data from an existing pool of 51 typical readers (aged 7.5-12.5 years). Sample sizes ranged between 20 and 1,000 participants and for each sample size 1,000 replications were run. Results were evaluated using chi-square Type I errors, model convergence, mean RMSEA (root mean square error of approximation) values, confidence intervals of the RMSEA, structural path stability, and Δ-Fit index values. Results suggested that 70 to 80 participants were adequate to model relationships reflecting close to not so close fit as per MacCallum et al.'s recommendations. Sample sizes of 50 participants were associated with satisfactory fit. It is concluded that structural equation modeling is a viable methodology to model complex regional interdependencies in brain activation in pediatric populations.

AB - The present study assessed the impact of sample size on the power and fit of structural equation modeling applied to functional brain connectivity hypotheses. The data consisted of time-constrained minimum norm estimates of regional brain activity during performance of a reading task obtained with magnetoencephalography. Power analysis was first conducted for an autoregressive model with 5 latent variables (brain regions), each defined by 3 indicators (successive activity time bins). A series of simulations were then run by generating data from an existing pool of 51 typical readers (aged 7.5-12.5 years). Sample sizes ranged between 20 and 1,000 participants and for each sample size 1,000 replications were run. Results were evaluated using chi-square Type I errors, model convergence, mean RMSEA (root mean square error of approximation) values, confidence intervals of the RMSEA, structural path stability, and Δ-Fit index values. Results suggested that 70 to 80 participants were adequate to model relationships reflecting close to not so close fit as per MacCallum et al.'s recommendations. Sample sizes of 50 participants were associated with satisfactory fit. It is concluded that structural equation modeling is a viable methodology to model complex regional interdependencies in brain activation in pediatric populations.

UR - http://www.scopus.com/inward/record.url?scp=84906872045&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906872045&partnerID=8YFLogxK

U2 - 10.1177/0013164414525397

DO - 10.1177/0013164414525397

M3 - Article

VL - 74

SP - 733

EP - 758

JO - Educational and Psychological Measurement

JF - Educational and Psychological Measurement

SN - 0013-1644

IS - 5

ER -