RECSM Winter School - February 16-18
The third edition of RECSM Winter Methods School (February 16-18, 2022) is comprised of one course. This online course lasts for three days, with four-hour long lectures per day.
The course is open to academics (students, professors, individuals employed by colleges and universities, and other institutions of higher education) and non-academics (consultants and other practitioners from the private sector or national and international organizations).
- Course fee: 250€.
Mode of instruction
You can pay with a bank transfer or credit/debit card.
All refund/cancellation requests must be provided via email to [email protected] and received prior to January 10th, 2022. From January 11th cancellation will not be refunded.
Invoices are sent upon demand.
- Instructor: Terrence Jorgensen, University of Amsterdam.
- Mode of teaching: Online
- Course fees: 250€
- Dates: February 16-18
- 10:00 - 14:00 CET
Structural equation modeling (SEM) is a very general statistical technique, as it has regression analysis, path analysis, and factor analysis as special cases. It is also possible to combine the advantages of these techniques, which makes SEM one of the most general and most flexible techniques available to researchers. As a result, SEM presently is also one the most widely used techniques in the social and behavioral sciences.
This course will introduce you to the fundamentals of SEM by first translating some familiar methods (t tests and ANOVA, regression and correlation) into mean and covariance structure (MACS) analyses. Then you will see how path analysis is more general than the general(ized) linear model and better able to facilitate testing hypotheses about mediation. The second day will introduce tactics for evaluating data–model correspondence and introduce measurement models for latent variables. Day 3 will cover path analysis and moderation involving latent variables—the latter of which requires evaluating measurement invariance—and end with how to handle common nonideal data.
All instruction and example syntax will utilize the latest version of the statistical software environment R, as well as the latest versions of add-on packages lavaan and semTools. Students are encouraged to reproduce analyses using the example data provided, as well as using their own data whenever possible.
Besides familiarity and some experience with R, students are expected to be familiar with the fundamental statistical concepts (e.g., descriptive and inferential statistics, null-hypothesis significance testing) as well as the general(ized) linear model (GLM) and its special cases: regression, t tests, ANOVA, and correlation. Familiarity with basic psychometrics (classical test theory, reliability, and validity) are helpful, especially for the portion of the course involving latent variables. Given the frequency with which SEMs are communicated using matrices (even in applied literature), some familiarity with basic matrix algebra is advantageous but not strictly necessary.
Introduction to lavaan: Mean and Covariance Structures
Exercises: SEM approach to regression, t tests, AN(C)OVA
Path analysis, indirect effects (mediation)
Exercises: Path analysis
Confirmatory factor analysis (CFA)
Structural regression with latent variables
Exercises: Full SEM
Testing hypotheses implied by a SEM: A trilogy of tests
Exercises: Model comparison
Global and local indices of approximate data–model fit
Exercises: Honest evaluation of model fit
References and Recommended Reading
Foundational texts about general(ized) linear modelling and hypothesis testing:
- Judd, C. M., McClelland, G. H., & Ryan, C. S. (2017). Data analysis: A model comparison approach to regression, ANOVA, and beyond (3rd ed.). New York, NY: Routledge. ISBN-13: 9781138819832
- Fox, J. (2016). Applied regression analysis and generalized linear models (3rd ed.) Los Angeles, CA: Sage.
Introductory and advanced SEM texts:
- Beaujean, A. A. (2014). Latent variable modeling using R: A step-by-step guide. Routledge.
- Bollen, K. A. (1989). Structural equations with latent variables. Wiley.
- Loehlin, J. C., & Beaujean, A. A. (2016). Latent variable models: An introduction to factor, path, and structural equation analysis. Taylor & Francis.
- Hoyle, R. H. (Ed.). (2012). Handbook of structural equation modeling. Guilford.
Reporting SEM results:
- Boomsma, A. (2000). Reporting analyses of covariance structures. Structural Equation Modeling, 7(3), 461–483. https://doi.org/10.1207/S15328007SEM0703_6
- McDonald, R. P. & Ho, M. R. (2002). Principles and practice in reporting structural equation analyses. Psychological Methods, 7(1), 64–82. https://psycnet.apa.org/doi/10.1037/1082-989X.7.1.64