Structural Equation Modeling

Petri Nokelainen (petri.nokelainen@tuni.fi)

Learning material

Lectures [PPT]

Structural Equation Modeling with
R lavaan (new)

AMOS [PDF] [Data] (not updated)
Mplus [PDF] [Data] (not updated)

Literature

Bollen, K. (1989). Structural Equations with Latent Variables. New York: John Wiley & Sons.

Kaplan, D. (2000). Structural Equation Modeling. Foundations and Extensions. Thousand Oaks: Sage.

Raykov, T., & Marcoulides, G. (2000). A First Course in Structural Equation Modeling. Mahwah, NJ: Lawrence Erlbaum Associates.

Schumacker, R. E., & Lomax, R. G. (2004). A Beginner's Guide to Structural Equation Modeling. Second edition. Mahwah, NJ: Lawrence Erlbaum Associates.

Articles

Nokelainen, P., Silander, T., Ruohotie, P., & Tirri, H. (2007). Investigating the Number of Non-linear and Multi-modal Relationships between Observed Variables Measuring a Growth-oriented Atmosphere. Quality & Quantity, 41(6), 869-890. [PDF]

Tirri, K., Nokelainen, P., & Komulainen, E. (2013). Multiple Intelligences: Can they be measured? Psychological Test and Assessment Modeling, 55(4), 438-461. [PDF]

Links

Quantitative Analysis Using SEM

R [(RStudio/lavaan/semPlot)]

AMOS [Trial (Win)]

LISREL [Trial/Student (Win)]

EQS [Student (Win/Mac/Linux)]

MPlus [Demo (Win/Mac/Linux)]

Assignment (choose one)

1. Write a 1500 - 2000 word essay that describes a pratical scenario of applying structural equation modeling (SEM) to your own research. Here are few starting points: Try to formulate at least one quantitative research question / problem that could be solved with SEM. Describe how you would use SEM to solve the problem: Write about the method, including at least description of real or fictive sample, data collection, statistical procedures and which one of the SEM approaches (e.g., CFA, path analysis) you choose to use. Try to ponder pros and coins of this approache. Memorize lectures and read articles, at least those provided in the course and refer to them using APA -style references.

2. Complete exercises in the “Structural Equation Modeling with R lavaan”. Exercises to be completed are indicated in the .Rmd document. When you have completed all the exercises, “knit” (i.e., produce output) the document into HTML, WORD or PDF file. Note that HTML and WORD outputs are easier to get working than PDF.