n-Level SEM With Small to Moderate Samples

• In Event: AERA Virtual Poster Session 2
  In Poster Session: Structural Equation Modeling

Abstract

A practical limitation of SEM is how to effectively estimate model parameters with typical sample sizes when there are many levels of (potentially disparate) nesting. We develop a method of moments corrected maximum likelihood estimator for n-level SEMs (SEMs with an arbitrary number of levels of nesting) that is well-suited to the types of small to moderate sample sizes typically seen in education. We probe the consistency, variability and convergence of the estimator with small/moderate n-level samples. The estimator emerges as a practical alternative to conventional full information estimators because it often outperforms them in small/moderate n-level samples. The results are implemented in the [BLINDED] R package and illustrated through an n-level teacher development example.

Authors

• Benjamin Kelcey, University of Cincinnati

• Fangxing Bai, University of Cincinnati

• Kyle T. Cox, University of North Carolina - Charlotte