Swiss Summer School 2017

Multilevel Structural Equation Modeling

** Elmar Schlüter** is Professor of Sociology, with focus on methods of cross-national comparative social research,
at the University of Giessen. His current research interests focus on the intersection of theories and methods for the
explanation of multilevel phenomena, particularly in the field of interethnic relations & social problems.
[Web page]

The primary objective of this course is to provide participants with a proper understanding and the practical skills necessary for applying advanced techniques in structural equation modeling to hierarchically ordered multilevel data structures. Core topics of the course include random intercept & slope models, contextual effect models, twolevel confirmatory factor analyses and twolevel structural equation models, moderation and mediation in twolevel SEM, and further topics. In order to put these different techniques to practice, participants will also become proficient in the use of the Mplus statistical software. Throughout the course, an emphasis will be put on how to achieve an adequate balance between theoretical assumptions, methods of data analysis and interpretation of the results. To facilitate the transfer of theoretical knowledge into participants' own research, a large part of the course will be devoted to systematic exercises using freely available survey data such as the Mosaich-ISSP or the Swiss Electoral Studies. Participants are encouraged, however, to also use their own data.

- Heck, R. H. & Thomas, S. L. (2009). An Introduction to Multilevel Modeling Techniques, pp. 75-97. Second Edition. New York: Routledge.
- Marsh, H.W., Lüdtke, O., Robitzsch, A., Trautwein, U., Asparouhov, T., Muthén, B.O., & Nagengast, B. (2009). Doubly-latent models of school contextual effects: Integrating multilevel and structural equation approaches to control measurement and sampling error. Multivariate Behavioral Research, 44, 764-802.

This course is at an advanced to intermediate level. In other words, it is designed for application-oriented participants who are already familiar with the basics of SEM (e.g. conducting and interpreting a confirmatory factor analysis) plus, ideally, multilevel analysis (e.g. conducting and interpreting a random intercept model), and would now like to expand their scope.

EH
Last update:
08.12.2016