Workshop B: Latent variable modeling with Lavaan

Tuesday afternoon, June 15, 13-16 CET

Structural equation modeling (SEM) is a general statistical modeling technique to study the relationships among observed and unobserved (latent) variables. It spans a wide range of multivariate methods to analyse a large variety of statistical models, including path analysis, structural equation modeling, and confirmatory factor analysis.

This workshop will provide both a refresher of SEM concepts and practices, and a tutorial on how to use the open-source R package ’lavaan’ ( The workshop will be based on lecture-style presentation.

The workshop targets all applied researchers who wish to employ some form of structural equation modeling to analyze their substantive research questions. Participants are supposed to be familiar with regression analysis and (exploratory) factor analysis. Some basic knowledge about R is recommended, but not required.

Please install the latest version of R ( and the R package ’lavaan’ ( for instructions) .

A brief summary of the workshop is as follows:

  • SEM basics
  • Model estimation, model evaluation, and model respecification
  • Introduction to lavaan

Workshop leader

This workshop will be led by Dr. Mariska T. Barendse

Dr. M. T. Barendse studied at the University of Amsterdam and obtained a research master (cum laude) in the field of educational science with a strong focus on methods and statistics. From 2010 to 2014, she was a PhD candidate at the Department of Psychometrics and Statistics of the Heymans Institute for Psychological Research at the University of Groningen and finished her PhD titled ”Dimensionality assessment with factor analysis methods” in 2015. After being a statistical consultant for nine months, she worked a post-doc at Ghent University. In 2019 she was appointed as an assistant professor at the Erasmus University in Rotterdam. In 2021 she started as a researcher at the Max Planck institute in Nijmegen. Her main research focus is the development and applications of statistical models using non-standard application structural educational modeling including exploratory factor analysis, multilevel modeling, genetic modeling, and the analysis of discrete data.