Install the app
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Menu
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Monday 7 ꟷ Friday 11 February 2022
Minimum of 2 hours live teaching per day
14:00 ꟷ 17:00
VIR: This is a virtual course
This online course provides a highly interactive teaching and learning environment, using state of the art online pedagogical tools. It is designed for a demanding audience (researchers, professional analysts, advanced students) and capped at a maximum of 16 participants so that the teaching team (the Instructor plus one highly qualified Teaching Assistant) can cater to the specific needs of each individual.
This course introduces you to the wondrous world of Structural Equation Modelling (SEM).
We will focus on the statistical foundation of this approach, the estimation of SEMs (using the R package Lavaan), and the interpretation of SEM results. Using a mixture of prerecorded lectures, interactive sessions and practical exercise, you will cover topics such as latent variable modelling, direct and indirect effect estimation, multigroup analysis and model fit evaluation.
3 credits Engage fully with class activities
4 credits Complete a post-class assignment
Bart Meuleman is a Full Professor at the Centre for Sociological Research, KU Leuven (Belgium).
His research focuses on cultural and socio-economic conflict lines in increasingly diverse societies. He has studied the structure and roots of intergroup attitudes, and ethnic threat perceptions and prejudices, from a majority and a minority perspective. He is particularly interested in how increasing migration movements and ethnic diversity affect preferences for welfare redistribution and social justice.
Bart's methodological research interests include comparative survey analysis, attitude measurement, structural equation modelling and multilevel models.
Bart is the National Coordinator of ESS Belgium, co-supervisor of the Belgian National Elections Study and the Belgian Ethnic Minority Elections Study 2014 and 2019, and a member of the Methodology Group of the European Values Study.
Over the course of five modules (one per day), a variety of topics fundamental to SEM will be covered.
Basics of SEM. What is the difference between SEM and more conventional multivariate techniques, such as regression analysis? What are the advantages and specificities of the SEM approach? You will learn important terminology and notation systems, and get an overview of different models in the SEM tradition.
We highlight a particular branch in the SEM family: latent variable models / measurement models / confirmatory factor analysis. This application allows us to discuss the issues of model specification, parameter estimation, model restrictions and identification in greater depth.
Provides three different approaches to SEM estimation that each imply a different epistemological position. We review the wide variety of procedures to evaluate model fit, and discuss the assumptions of the SEM model.
Focuses on a second branch of the SEM approach: structural models. We cover examples such as path analysis, structural regression models and MIMIC models.
Introduces the concept of multigroup SEM, and illustrates how to use this approach in comparative research (including tests for measurement equivalence).
Please prepare for each module by watching the short prerecorded lectures (typically three 15-minute lectures per module), complete the essential readings, and a short hands-on exercise analysing real data using the R package lavaan.
During our daily two-hour interactive session, we will discuss examples and additional topics in greater detail, and you'll have ample opportunity to ask questions and get feedback. The Instructor and TA will make themselves available for one-to-one online consultation during specified hours, giving you the chance to seek advice on personal research projects.
Basic background knowledge in statistics (descriptive statistics, null-hypothesis testing, and regression analysis) is required.