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”
Member rate £492.50
Non-Member rate £985.00
Save £45 Loyalty discount applied automatically*
Save 5% on each additional course booked
*If you attended our Methods School in Summer/Winter 2024.
Monday 31 July - Friday 4 August and Monday 7 - Friday 11 August
09:00-12:30
Please see Timetable for full details.
The course gives an introduction to theory and practice of Structural Equation Modelling (SEM).
It is shown how theoretical latent constructs (e.g. social and political attitudes, values, and intentions) can be operationalised and how their causal relationships can be tested. The course introduces to the logic of SEM using computer software AMOS but shows how to use lavaan (R) and Mplus as well.
The first part of the course introduces the specification of Confirmatory Factor Analysis (CFA) as a special case of SEM. Measurement models with single or multiple indicators of latent variables are estimated and tested. Different modelling specifications will be introduced including multiple group analysis (e.g. to test measurement equivalence across different social groups or countries). The second part of the course deals with specification and test of causal structural equation models (e.g. MIMIC models (Multiple Indicators and Multiple Causes), assessment of models, mediation and moderation, feedback loops).
Jochen Mayerl has been a researcher and lecturer in empirical methods of Social Sciences at University of Kaiserslautern since March 2013.
From November 2001 to February 2013, he lectured in Sociology and empirical social research at the University of Stuttgart, where he has taught various research and analysis methods. He finished his doctoral thesis, Cognitive foundations of social behaviour: theoretical and statistical analysis of attitude-behaviour relations, in 2008. During the winter term 2011/2012, he was substitute professor at the University of Kassel, Germany.
His main research interests in methodology are new developments and applications in structural equation modelling, response effects in surveys, and response latency measurement in computer assisted surveys.
He has published in the field of methodology as well as sociological theory (attitude-behaviour research, bounded rationality, framing) and substantial research (e.g. donation behaviour, environmental concern, ethnocentrism, political attitudes).
Structural Equation Modelling (SEM) is a powerful tool to analyse latent variable models that are common in social sciences, e.g. the analysis of personality factors, social and political attitudes, social values, and behavioural intentions. SEM combines factor analysis and path analysis by simultaneously estimating causal relations between latent constructs and relations of latent constructs and its corresponding manifest indicators in the measurement models. Additionally, SEM allows the estimation and control for random and systematic measurement errors. Thus, SEM methodology allows an adequate modelling and empirical testing of measurement models and complex theoretical assumptions.
The course introduces to theory and practice of SEM on a general level. The course starts using the software AMOS but introduces into lavaan (R) and Mplus as well.
Basic modelling techniques of SEM are explained and applied by exercises using free access social science data. Additionally, participants have got the possibility and are encouraged to use their own data for analyses. Exercises allow the application and transfer of SEM methodology to own research interests.
The first part (week 1) of the course introduces to principles of Structural Equation Modelling. It is shown how Confirmatory Factor Analysis (CFA) can be specified and estimated, i.e. how latent constructs (e.g. attitudes, values, behavioural intentions) can be operationalised by multiple manifest indicators and how these measurement models can be tested empirically. The first week includes the following topics:
In the second part of the course (week 2), full SEM is introduced to specify and estimate causal relations between latent constructs and thus to test theoretical hypotheses. Additionally, advanced techniques of SEM and special problems will be illustrated and discussed.
Participants should understand basic principles of regression analysis and the meaning of regression results. A basic understanding of principal component analysis (explorative factor analysis) would be helpful. Participants should be familiar with software to manage data (e.g. SPSS, STATA, R).
Day | Topic | Details |
---|---|---|
Monday 1 | Introduction to SEM |
3 hours lecture and exercises |
Tuesday 2 | Basic principles of SEM; Confirmatory Factor Analysis (CFA); measurement models |
1.5 hours lecture – 1.5 hours exercises |
Wednesday 3 | Fit Indices; CFA: step by step; test of normality & outliers; second order measurement models; method factors |
1.5 hours lecture – 1.5 hours exercises |
Thursday 4 | Multiple Group CFA: testing measurement equivalence |
1.5 hours lecture – 1.5 hours exercises |
Friday 5 | Multiple Group CFA: Latent means |
1.5 hours lecture – 1.5 hours exercises |
Monday 8 | Full SEM; model testing strategies; MIMIC models |
1.5 hours lecture – 1.5 hours exercises |
Tuesday 9 | Mediation, decomposition of causal effects: direct, indirect and total effects; feedback loops |
1.5 hours lecture – 1.5 hours exercises |
Wednesday 10 | Multiple group SEM and moderation, SEM with meanstructure; sample size in SEM |
1.5 hours lecture – 1.5 hours exercises |
Thursday 11 | Special topics of SEM: categorical indicators and non-normality (incl. bootstrapping); interaction effects; missing value treatment; nonlinearity; formative measurement models |
1.5 hours lecture – 1.5 hours exercises |
Friday 12 | Open questions and presentation of participant’s models; Advanced techniques (e.g. cross-lagged autoregressive models, latent growth curve models); Discussion (“overfitting”, how to fool yourself with SEM); How to report SEM results |
1.5 hours lecture – 1.5 hours exercises |
Saturday 13 | Exam |
Day | Readings |
---|---|
Monday 1 |
Byrne 2016: chapter 1 and 2 (introduction to SEM and AMOS) |
Tuesday 2 |
Byrne 2016: chapter 3 (CFA);
|
Wednesday 3 |
Byrne 2016: chapter 4 (CFA) and 5 (second order CFA)
|
Thursday 4 |
Byrne 2016: chapter 7 (multigroup CFA)
|
Friday 5 |
Byrne 2016: chapter 8 (multigroup CFA with meanstructure)
|
Monday 6 |
Byrne 2016: chapter 6 (full SEM)
|
Tuesday 7 |
Maruyama 1998: pp. 35-48 (effect decomposition); Kline 2016: pp. 239-253 (effect decomposition), pp. 150-157 (non-recursive models) |
Wednesday 8 |
Byrne 2016: chapter 9 (multigroup full SEM) |
Thursday 9 |
Byrne 2016: chapter 12 (bootstrapping) and 13 (missing data);
|
Friday 10 |
Kline 2011: chapter 13 (How to fool yourself with SEM); Kline 2016: chapter 18 (best practices); Boomsma 2000 (reporting SEM results) |
IBM SPSS Amos 24; a trial version is available for download at:
http://www-01.ibm.com/support/docview.wss?uid=swg24041666
R (version 3.3.1 or higher) with RStudio Desktop (version 0.99.902 or higher) and R packages: (lavaan version 0.5-20 or higher; foreign; semTools, qgraph; semPlot)
Computer lab, no other specific requirements
Arbuckle, J. L., 2016: IBM SPSS Amos 24 User’s Guide. Armonk, NY: IBM.
Bollen, K. A., 1989: Structural equations with latent variables. New York: John Wiley and Sons.
Boomsma, A., 2000: Reporting analyses of covariance structures. Structural Equation Modelling, 7(3), 461-483.
Brown, T. A., 2015: Confirmatory Factor Analysis for Applied Research (2nd edition). New York/London: Guilford.
* Byrne, B. M., 2016: Structural Equation Modeling with AMOS. Basic Concepts, Applications and Programming (3rd edition). New York/London: Routledge.
* Kline, R. B., 2016: Principles and Practice of Structural Equation Modeling (4th edition). New York/London: Guilford.
Kline, R. B., 2011: Principles and Practice of Structural Equation Modelling (3rd edition). New York/London: Guilford.
Maruyama, G. M., 1998: Basics of structural equation modelling. Thousand Oaks: SAGE Publications, Inc.
Ping, R.A., 1996: Latent Variable Interaction and Quadratic Effect Estimation: A Two-Step Technique Using Structural Equation Analysis. Psychological Bulletin 119 (1): 166-175.
Schafer, J. L./Graham, J. W., 2002: Missing Data: Our View of the State of the Art. Psychological Methods 7(2): 147-177.
Schumacker, R. E./Lomax, R. G., 2016: A beginner`s guide to structural equation modeling (4th edition). Mahwah: Lawrence Erlbaum Associates.
Winter School
Structural Equation Modeling (SEM) with R - Ulrich Schröeders
Summer School
Introduction to Inferential Statistics: What you need to know before you take regression – Levente Littva
Multiple Regression Analysis: Estimation, Diagnostics, and Modelling – Michael Dorsch
Advanced Topics in Applied Regression - Constantin Manuel Bosancianu
Winter School
Structural Equation Modeling (SEM) with R - Ulrich Schröeders
Summer School
Multi-Level Structural Equation Modelling
Advanced Structural Equation Modeling