Structural Equation Modeling

Thu - Tue, Sept 27 to Okt 2, 10:00am - 4:00pm

Hestia Hotel Europa, Paadi 5, Tallinn

Lecturer: Levente Littvay, Associate Professor of Political Science at Central European University, Budapest, Hungary 

The course is designed to provide scholars with a basic understanding of structural equation modeling (SEM). Special attention is given to the translation of theoretical expectations into SEM, the interpretation of results in SEM analyses and the general use and misuse of SEM in the social sciences. While the course is predominantly designed to give you the knowledge of SEM we start with a quick introduction of necessary foundations like correlations, covariances, regression and factor analysis. Applications will include path models, factor analyses and structural equation models, and, if time allows, a bit of multilevel SEM. The goal of the course is to o er a basic
introduction and the foundation for students to start using and critically assessing SEM and also have the ability to independently discover and master advanced SEM statistical topics. Course overview.

Upon completion the students will have a basic conceptual understanding of SEM and its statistical foundations. Students will be able to critically assess the appropriateness of such techniques in their own and other people's research and conduct SEModeling themselves to the highest academic standards.

REGISTRATION open until 5 September 2018

Pre-requisites for the Class
The class is open to experienced researchers (advanced MA students, PhD students and interested faculty) as long as their prior statistical training allows. Anyone entering the course should be an experienced user of regression, know the basics of inferential statistics and should have heard of factor analysis, at least at the informed consumer level.

Week Topics
Sept 27 Session 1 Review of Regression and Factor Analysis
Sept 27 Session 2 Intro to SEM
Sept 27 Session 3 SEM Fundamentals and Path Models
Sept 28 Session 1 Measurement Models with Multiple Indicators
Sept 28 Session 2 Measurement Models with Fewer Indicators
Sept 28 Session 3 Measurement Models II
Oct 1 Session 1 Structural Models
Oct 1 Session 2 More Structural Models
Oct 1 Session 3 Multiple Groups
Oct 2 Session 1 Moderation and Mediation and Non-normality
Oct 2 Session 2 Weird Models (Growth Curve, Cross-Lag and ACE)
Oct 2 Session 3 Big Picture: Thinking Theoretically. Formative vs Re ective Models

Technical information

Please Bring Your Computers with R and Lavaan installed.

Mayerl, Jochen and Levente Littvay (forthcoming) Structural Equation Modeling. SAGE

Additional Resources
Kline, Rex B. (2016) Principles and Practice of Structural Equation Modeling. 4th ed. The Guilford Press
Finkel, Steven E. (1995) Causal Analysis with Panel Data. SAGE
Singer, Judith and John Willett (2003) Applied Longitudinal Data Analysis: Modeling Change and Event Occurrence. Oxford University Press

The programme in all days:
10.00-11.30 Session 1
11.30-12.00 Coffee break
12.00-13.30 Session 2
13.30-14.30 Lunch (self-organised)
14.30-16.00 Session 3

Contact person
Koidu Saia
Research Coordinator  

Accommodation and other travel costs for PhD students from Tartu will be reimbursed if You contact Your doctoral school coordinator:
Doctoral School in Economics&Innovation - Katrin Tamm,
Doctoral School of Behavioural, Social and Health Sciences - Maris Meus,

This event is financially supported by Project TU TEE - Tallinn University as a Promoter of Intelligent Lifestyle