Introduction into Structure Equation Modeling using Mplus
In this two-day workshop, participants will learn how to use Mplus to analyze data from international large-scale assessments (ILSAs) such as ICCS and PISA. Focusing on data from PISA 2018, the workshop will guide learners through the preparation of data for Mplus, help them understand the basics of Mplus syntax, and how to account for the clustered structure of PISA data. Finally, the imputation technique will be introduced so that knowledge scores can be used correctly.
Participants should be familiar with key statistical concepts such as effect size and regression. Attendees are required to bring a laptop with Mplus installed, along with additional statistical software (e.g., SPSS or R) for dataset preparation. While experience with syntax-based software is beneficial, it is not a prerequisite.
Structure of the workshop
14.11.2024
09:00-09:30 Arrival and introductions
09:30-10:15 The language & logic of Mplus
10:15-10:40 Hands-on training
10:40-11:00 Coffee break
11:00-11:45 Regressions & SEMs in Mplus
11:45-12:00 Hands-on training
15.11.2024
09:00-09:30 Arrival, questions & repetitions
09:30-10:15 Using weights and accounting for the multilevel structure
10:15-10:40 Hands-on training
10:40-11:00 Coffee Break
11:00-11:45 Using plausible values
11:45-12:10 Hands-on training
12:10-12:30 Wrap up
Recommended reading:
West, S. G., Taylor, A. B., & Wu, W. (2012). Model fit and model selection in structural equation
modeling. Handbook of structural equation modeling, 1(1), 209-231
Rutkowski, L., Gonzalez, E., Joncas, M. & Davier, M. von (2010). International Large-Scale Assessment
Data. Educational Researcher, 39(2), 142–151. doi.org/10.3102/0013189X10363170
Mplus Quickstarter:
global.oup.com/us/companion.websites/9780195367621/pdf/MplusQuickGuide2015.pdf
Further reading:
Basic introduction (somewhat old, but very understandably written)
Geiser, C. (2010). Data Analysis with Mplus.
Concerning centering:
Asparouhov, T. & Muthén, B. (2019). Latent variable centering of predictors and mediators in
multilevel and time-series models. Structural Equation Modeling: A Multidisciplinary Journal, 26(1),
119–142. doi.org/10.1080/10705511.2018.1511375
When creating scales that are to be used in different many different groups:
Munck, I., Barber, C. & Torney-Purta, J. (2017). Measurement invariance in comparing attitudes
toward immigrants among youth across Europe in 1999 and 2009: The alignment method applied to
IEA CIVED and ICCS. Sociological Methods & Research, 47(4), 687-728.
doi.org/10.1177/0049124117729691
Important paper on model fit:
Rutkowski, L. & Svetina, D. (2014). Assessing the hypothesis of measurement invariance in the
context of large-scale international surveys. Educational and Psychological Measurement, 74(1), 31–
57. doi.org/10.1177/0013164413498257
Further reading on model fit:
Carle, A. C. (2009). Fitting multilevel models in complex survey data with design weights:
Recommendations. BMC medical research methodology, 9, 49. doi.org/10.1186/1471-2288-
9-49
Complex survey data:
Muthen, B. O. & Satorra, A. (1995). Complex sample data in structural equation modeling.
Sociological Methodology, 25, 267. doi.org/10.2307/271070