An Introduction to Confirmatory Factor Analysis (CFA) and Structural Equation Modeling (SEM): Investigating linear relationships among latent constructs

Abstract

This was presented in August 2016 to the EARLI SIG 1 Assessment and Evaluation Summer School in Munich. It provides an introduction to CFA and SEM techniques. It presumes understanding of exploratory factor analysis and multivariate statistical techniques. It extends basic CFA into SEM and multigroup invariance testing. It illustrates procedures and problems that can occur in testing models (e.g., negative error variance, not positive definite covariance matrices) and suggests solutions to overcome these issues. All illustrations are given using AMOS software.