Introduction to Structural Equation Modeling (paid version for the professional)

Social scientific theories often imply complex patterns of relations that cannot be adequately evaluated with simple statistical tests or univariate statistical models. This course introduces structural equation modeling (SEM): a flexible statistical modeling technique with which you can represent complex theories and test those theories against empirical data. SEM combines factor analysis with path modeling. The former gives SEM the ability to model unobserved hypothetical constructs via estimated latent variables, and the latter allows SEM to model complex patterns of relations among these latent variables. 

This course will systematically build up the fundamental principles of SEM and the basic techniques of SEM-based analyses. We will start by considering what we really mean by a "statistical model", and we'll explore the process of translating a social scientific theory into a formal statistical model. We will then combine these new statistical modeling concepts with your prior knowledge of linear regression to motivate our discussion of path analysis. From there, we'll consider how factor analysis allows us to rigorously define, estimate, and evaluate theoretical measurement models of the hypothetical constructs we wish to analyze. Finally, we will conclude by combining all of these components into a fully realized SEM.

Throughout the course, you will apply your new knowledge to real data analyses via weekly practical exercises and two summative assignments. All analyses will be conducted in the R statistical programming language. R is a freely available, open-source statistical software package that is available to anyone. No prior knowledge of R or programming is required.

Assumed Prior Knowledge: Basic theoretical understanding of statistical testing (e.g., t-test, ANOVA), linear regression, and correlation. Participants should have some experience working with a statistical software program (e.g., R, JASP, SAS, STATA, SPSS) to conduct statistical tests and linear regression analyses.

Note: Students who cannot comply with the entrance requirements mentioned below will be asked to provide further information on their eligibility. The course coordinator will decide if the student's prior experience is sufficient to follow the course.