Applying structural equation modelling in educational research

Structural equation modelling (SEM) is a comprehensive and flexible statistical technique for testing complex relationships between variables, including both observed variables and latent variables (constructs or factors), with multiple pathways. In the past two decades, SEM has quickly pervaded in various research fields, such as psychology, sociology, education, economics, etc. This study provides a brief non-mathematical introduction to SEM for educational researchers who are interested in SEM but do not have advanced statistical backgrounds. This study presents the basic concepts of SEM, describes the steps of SEM implementation and discusses some issues that are often encountered in SEM applications. Examples of measurement model (confirmatory factor analysis, CFA) and general structural equation model are demonstrated, using real educational research data. Computer program Mplus was applied for modelling; the programming syntax and selected output for the example models are included.