Structural equation modelling

blue and yellow writing in light

Introduction


Key terms: quantitative research, structural equation modelling, correlational analysis, causality, R-lavaan software package, introductory course, relevant for students in any PhD phase

ECTS: 2.5 
Number of sessions: 4
Hours per session: 3

Structural equation modelling (SEM) is used to test a theory or hypothesis about how multiple constructs are related to one another. A construct can be a cause of an outcome or the outcome itself.

With SEM it’s possible to assess constructs that can be observed and measured directly, or constructs that cannot be observed and measured directly and are therefore ‘latent’.

For example, you can use SEM to test whether the relationship between higher body weight (observed variable) and more depressive symptoms (latent variable, assessed by several indicators) is mediated by a more negative self-concept (latent variable, assessed by several indicators).

The course will explain both the measurement part of the model (i.e. confirmatory factor analysis, linking indicators to latent variables) and the structural part of the model (also linking latent variables amongst each other). We will also discuss how SEM can be used to test hypotheses about mediation and moderation, and about change when longitudinal data are available.

Participants will learn how to fit a SEM model to the data in the software program R-lavaan. The meetings will consist of mini-lectures and the opportunity to practice with structural equation modelling in R using both exercise data and your own data.

Please note that for making notes and completing assignments, participants need to bring a laptop to each class meeting.
 

Entry level and relevance


This course is relevant for students in any PhD phase who conduct quantitative research on correlations or cause-effect relations between variables.

To attend the course properly, however, participants should ideally have basic knowledge of the program R. If you do not have such knowledge yet, you can first follow the EGSH course Data literacy through R. If you doubt whether you have sufficient knowledge about R, please contact the lecturer, Marleen de Moor.

 

Relations with other courses


This course builds on the EGSH course Data literacy through R. Further, structural equation techniques can be combined with multilevel modelling techniques, so following this course together with the EGSH course Multilevel modelling is useful if students are interested in multilevel SEM . These courses can be followed independently from each other, and it does not matter in which order they are attended.

Key Facts & Figures

Type
Course
Instruction language
English
Mode of instruction
Offline

Start dates for: Structural equation modelling

Edition 1

Session 1: March 4 (Wednesday) 2026 | 13.30-16.30 hrs | Offline (Mandeville building, room T19-01)

Session 2: March 11 (Wednesday) 2026 | 13.30-16.30 hrs | Offline (Mandeville building, room T19-01)

Session 3: March 18 (Wednesday) 2026 | 13.30-16.30 hrs | Offline (Mandeville building, room T19-01)

Session 4: March 25 (Wednesday) 2026 | 13.30-16.30 hrs | Offline (Mandeville building, room T19-01)

Loading...

What will you achieve?

  • After this course, you will have knowledge about different types of SEM models.
  • After this course, you will understand the core statistical concepts in SEM.
  • After this course you will know how to use SEM for mediation and moderation.
  • After this course, you will know how to specify and estimate a SEM model, and interpret the results.
  • After this course, you are able to apply this acquired knowledge about SEM to your own data in your PhD project.

Sessions and preparations


Session 1: Introduction to SEM
In this session you will be introduced to the basic concepts relevant to understand SEM. You will learn how to draw path diagrams using specific conventions and you will learn how to formulate a model with a set of regression equations. You will learn how SEM is an extension of the regression model by specifying regression relationships among several outcome and predictor variables (e.g. a path model).
Preparations:
• Read chapter 1 (Fundamentals of structural equation modeling) of Raykov, T., & Marcoulides, G. A. (2000). A first course in structural equation modeling. Lawrence Erlbaum Associates. Available online (PDF)
• Read chapter 3 (Path analysis) of Raykov, T., & Marcoulides, G. A. (2000). A first course in structural equation modeling. Lawrence Erlbaum Associates.
• Download and install the free and open source programs R and Rstudio
 

Session 2:  Measurement models: Confirmatory factor analysis
In this session we will introduce the concept of a latent variable. You will learn how to specify and run a confirmatory factor model which connects latent variables to observed variables.
Preparations: read chapter 4 (Confirmatory factor analysis) of Raykov, T., & Marcoulides, G. A. (2000). A first course in structural equation modeling. Lawrence Erlbaum Associates.


Session 3: Structural models: Mediation and moderation
In this session, you will learn how to specify and run a full SEM model, including relationships among latent variables.
Preparations:
• Read chapter 5 (Structural regression models) of Raykov, T., & Marcoulides, G. A. (2000). A first course in structural equation modeling. Lawrence Erlbaum Associates. 
• Prepare questions on your own research.
 

Session 4: Structural equation models for longitudinal data
In this session, you will be introduced to different types of SEM models for longitudinal data, such as the cross-lagged panel model and the latent growth curve model.
Preparations:
• Read chapter 6 (Latent change analysis) of Raykov, T., & Marcoulides, G. A. (2000). A first course in structural equation modeling. Lawrence Erlbaum Associates.
• Before class, send in question about your own research. You will receive personal feedback during class.
 

Instructor

  • Marleen de Moor
    Marleen de Moor is an associate professor at the EUR Department of Psychology, Education and Child Studies, where she gives courses in research methodology and statistics. In her research she develops and applies advanced data analysis techniques such as multilevel analysis, structural equation modelling, factor analysis and time series analysis.
    Email address

Contact

Facts & Figures

Fee
  • free for PhD candidates of the Graduate School
  • €575,- for non-members
  • consult our enrolment policy for more information
Tax
Not applicable
Offered by
Erasmus Graduate School of Social Sciences and the Humanities
Course type
Course
Instruction language
English
Mode of instruction
Offline

Compare @count study programme

  • @title

    • Duration: @duration
Compare study programmes