Croon's Estimation of Structural Equation Models With Partially Nested Data

• In Event: AERA Poster Session 9
  In Poster Session: Structural Equation Modeling (San Diego)

Abstract

The purpose of this study was to extend and evaluate a structure after measurement approach (SAM) that uses Croon’s corrections to estimate structural equation models (SEM) with partial nesting. SEMs estimated using full information approaches (e.g., maximum likelihood) have proven effective in operationalizing complex multilevel systems common in educational research while accounting for latent variable unreliability. However, this approach often requires prohibitively large sample sizes. SAM-Croon’s has been effectively applied with limited sample sizes and complex SEMs but it has not been extended or evaluated with SEMs when data are partially nested. We developed these extensions and used simulation studies to demonstrate SAM-Croon’s is an effective alternative estimation approach for SEMs when data are partially nested.

Authors

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

• Benjamin Kelcey, University of Cincinnati

• Fangxing Bai, University of Cincinnati