The workshop introduces the analysis of longitudinal data using structural equation modeling (SEM), a flexible framework for modeling complex relationships among variables, latent constructs, and measurement error within a unified approach.

 

The first part covers path analysis and focuses on specifying, estimating, and interpreting longitudinal models, including autoregressive, fixed- and random-effects, cross-lagged, and latent growth curve models. The second part extends these models to latent variables measured by multiple observed indicators. Confirmatory factor analysis (CFA) for longitudinal data is introduced, with attention to correlated measurement errors over time and tests of measurement invariance across waves. These models are then formulated as full structural equation models. The third part addresses advanced topics, including the analysis of non-normal and categorical data, multiple-group models, and differences-in-differences estimation.

 

Throughout the workshop, theoretical concepts are combined with practical demonstrations using social science data from a panel survey of young people on values and attitudes toward crime. All modeling is conducted in the lavaan package in R. You work with prepared exercises and are encouraged to apply SEM methods to your own data for hands-on experience.

 

The three-day workshop is divided into lecture sessions and hands-on exercises, with materials provided by the instructor for both. You can discuss questions related to the lecture content, the exercises, and your own projects, with a focus on conceptual and analytical issues. Active participation in discussions, engagement with the exercises, and reading of the workshop literature are expected. You are also encouraged to work on your own projects and to analyse your own data, either individually or in small groups.

You will find the course useful if:

By the end of the course, you will:

 

To be able to follow the script and execute the exercises, you need a computer with the latest versions of R and RStudio installed. The installation files for R for Windows can be found here https://cran.r-project.org/bin/windows/base/ and for Mac here https://cran.r-project.org/bin/macosx/, while the current installation files for RStudio can be found here https://posit.co/download/rstudio-desktop.

 

The main R package used in this workshop is lavaan. Other useful packages are semTools, semPlot, descr, psych, and ggplot2.