2
Structural Equation Modeling (Psych 711)
Tuesday and Thursday 2:30-3:30pm, room634
Fall 2013
The goal of this class is to familiarize you with path analysis and structural equation modeling. After a short introduction on multiple regression analysis, we will spend most of the semester on models in which one or more variables are considered to be both effects and causes. We will start with causal models without latent variables (path analysis) and then move on to non-causal models with latent variables (confirmatory factor analysis), and causal models with latent variables (hybrid models). We will be using the statistics software R. Please know that extensive work outside the classroom is required in order to succeed in this class (both readings and statistical analyses with data sets). I want to encourage you to participate actively in the class, as participation is one of the best predictors of student learning.
Bibliography:
Kline, R. B. (2010). Principles and practice of structural equation modeling (third edition). New York, US: The Guilford Press
Yves Rosseel (2012). lavaan: An R Package for Structural Equation Modeling. Journal of Statistical Software, 48, 1-36. URL: http://www.jstatsoft.org/v48/i02/
lavaan web page: http://lavaan.ugent.be
lavaan tutorial: http://lavaan.ugent.be/tutorial/index.html
Program:
Week 1 (Sept. 3/5) – Introduction to R
Reading raw data files, computation of new variables, descriptive statistics, basic inferential statistics.
Week 2 (Sept. 10/12) – Fundamental concepts
Correlation and covariation, standardized and unstandardized predictors, simple and multiple regression.
Week 3 (Sept. 17/19) – Path analysis I
The logic of SEM, exogenous and endogenous variables, disturbances, unanalyzed relationships, sample covariance matrix, model covariance matrix, iterative estimation.
Week 4 (Sept. 24/26) – Path analysis II
Data preparation, data screening, specification.
Week 5 (Oct. 1/3) – Path analysis III
Under-identified, just-identified, and over-identified models, goodness-of-fit indices, the independence model.
Week 6 (Oct. 8/10) – Path analysis IV
Mediation, comparing hierarchical models, comparing non-hierarchical models (AIC)
Week 7 (Oct. 15/17) – Path analysis V
Multiple group analysis, equivalent and near-equivalent hierarchical models.
Oct. 16-18: MID-TERM EXAM 1 !!!! (exact date and time to be announced)
Week 8 (Oct. 22/24) – Confirmatory factor analysis I
Latent variables, specifying a unit of measurement for latent variables, estimating a one-factor CFA model, estimating a multi-factor CFA model.
Week 9 (Oct. 29/31) – Confirmatory factor analysis II
Hierarchical CFA models, CFA models with correlated errors, equivalent models, multiple-group CFA models
Week 10 (Nov. 5/7) – Hybrid models
Models with structural and measurement components, hybrid models with a just-identified structural component.
Week 11 (Nov. 12/14) – Hybrid models
Hybrid models with an over-identified structural component, reporting the results of SEM analyses, single indicators in hybrid models
Week 12 (Nov. 19/21) – Mean Structures in SEM
Logic of mean structures, estimation of mean structures.
Week 13 (Nov. 26) – Interaction effects in SEM
Interaction effects of observed variables, interaction effects of latent variables
Thanksgiving Recess: Nov. 28 – Dec. 1, 2013
Week 14 (Dec. 3/5) – How to fool yourself with SEM
Frequent mistakes at different stages of the research project, fit indices, SEM as a model comparison approach, equivalent and near-equivalent models
Week 15 (Dec.10/12) – Repetition and integration
Dec. 11-13: MID-TERM EXAM 2 !!!! (exact date and time to be announced)
Grades:
Group Work 20%
Participation 20%
Mid-term Exam 20%
Final Exam 40%
Other good books/articles on structural equation modeling:
Blunch, N. (2013). Introduction to Structural Equation Modeling Using IBM SPSS and Amos. Belmont, CA, US: Allyn & Bacon. (no need to buy this book).
Kaplan, D. W. (2008). Structural equation modeling: Foundations and extensions (second edition). Thousand Oaks, CA, US: SAGE Publications.
Schumacker, R. E., & Lomax, R. G. (2010). A beginner's guide to structural equation modeling (3rd ed.). Mahwah, NJ, US: Lawrence Erlbaum Associates.
Fox, J. (2006). Structural equation modeling with the sem package in R. Structural Equation Modeling, 13, 465-486.
Liu, S., Rovine, M. J., & Molenaar, P. C. M. (2012). Selecting a linear mixed model for longitudinal data: repeated measures analysis of variance, covariance pattern model, and growth curve approaches. Psychological Methods, 17, 15-30.
McArdle, J. J. (2009). Latent variable modeling of differences and changes with longitudinal data. Annual Review of Psychology, 60, 577-605.
Ferrer, E., & McArdle, J. J. (2010). Longitudinal modeling of developmental changes in psychological research. Current Directions in Psychological Science, 19, 149-154.
Where to take complaints about a Teaching Assistant or Course Instructor:
Occasionally, a student may have a complaint about a Teaching Assistant or course instructor. If that happens, you should feel free to discuss the matter directly with the TA or instructor. If the complaint is about the TA and you do not feel comfortable discussing it with him or her, you should discuss it with the course instructor. If you do not want to approach the instructor, make an appointment to speak to the Department Chair, Prof. Patricia Devine: .
If your complaint has to do with sexual harassment, you may also take your complaint to Vicky Lenzlinger, Administrative Program Specialist, . Her office is located on the second floor of the Psychology building, room 222.
If you believe the TA or course instructor has discriminated against you because of your religion, race, gender, sexual orientation, or ethnic background, you also may take your complaint to the Office of Equity and Diversity, room 179-A Bascom Hall, or go to: http://www.oed.wisc.edu/