Testing the Effectiveness of Muthén's Maximum Likelihood (MUML) Estimation Method for Dyadic Data in Multilevel Structural Equation Models

• In Event: 46.079 - Appropriate Modeling of Latent Growth and Relationships

Abstract

Multilevel structural equation modeling (MSEM) has become a widespread analytic technique for analysis of nested data. However, practices associated with the employing of MSEM with extremely small group sizes (e.g., dyads) are problematic due to the lack of empirical research. In the current study, a Monte Carlo simulation was employed to investigate the performance of MSEM with dyadic data using Muthén’s psudobalance approach. Results indicates the within-group part of the models poses no problems, however, for the between-group models, there exist estimation and convergence problems with small sample size and low ICC. Therefore, researchers should be cautious with the use of MCFA with dyadic data especially when the variability across dyads is of central interests.

Authors

• Yu Su, University of Florida

• Walter L. Leite, University of Florida