We offer a five-day course on how to perform basic SEM analyses using Mplus. The main objective of this course is to learn how to analyse several models with Mplus (e.g., path models, multiple group models, mediation and moderation, confirmatory factor analysis, and longitudinal models). No previous knowledge of Mplus is assumed, but prior knowledge of SEM, although not mandatory, will make this course more useful.
Many researchers in the social and behavioral sciences are using, or want to use, Structural Equation Modelling (SEM) to investigate their theories. Mplus is a popular and flexible software package for doing SEM. We offer a 5-day course on how to perform basic SEM analyses using Mplus, where you can interact with Mplus experts.
The course starts with an introduction on how to use Mplus to perform regression analysis and how to ‘communicate’ with Mplus (e.g., how to specify a model, and how to deal with error messages). In the following days, basic models relevant for social scientists will be discussed, including multiple group models, confirmatory factor analysis, and cross-lagged panel models, and important topics such as moderation, mediation and testing for measurement invariance are covered. These days consist of lectures by Mplus experts and computer labs where participants practice with Mplus. On the last day, you can meet with Mplus experts for individual consultation, and work on your own data.
Researchers are expected to have a basic knowledge of regression analysis and exploratory factor analysis (i.e., principal component analysis). These techniques are discussed in most books on multivariate statistics (e.g., Andy Field: Discovering Statistics; Tabachnick and Fidell: Using multivariate statistics).
Some knowledge of SEM and software like AMOS, LISREL, Mx or EQS is helpful, but not mandatory. If you have no experience with SEM, please read the following paper: Hox, J. J. & Bechger, T.M. (2007). An introduction to structural equation modelling. Family Science Review, 11, 354-373. Accessible via www.joophox.net.
No previous knowledge of Mplus is assumed. You also do not need to have any knowledge of matrix algebra, calculus, or likelihood theory.
The substantive content of this course largely overlaps with Summer School course Structural Equation Modeling in R using lavaan (S65), where each have their own specializations in the advanced topics. These two courses can, therefore, be viewed as largely equivalent alternatives that target different audiences by employing different software (i.e., Mplus vs lavaan) and instructional formats (i.e., on-location vs online/e-learning).
A good follow-up is our Summer School course ‘Advanced longitudinal modeling in Mplus’ (S23), where participants learn using SEM to analyze longitudinal data.
We also offer tailormade M&S courses and in-house M&S training. If you want to look the possibilities, please contact us at email@example.com
You will receive a certificate upon course completion. Please be aware that this course does not include graded activities, and therefore we cannot provide a transcript of grades.
Participants are requested to bring their own laptop computer. If needed, software will be available online.
Dr. Beth Grandfield, Pia Andrese and Jeroen Mulder
Participants (Research Master Students, PhD students, or post-graduate researchers) from a variety of fields, including sociology, psychology, education, human development, marketing, business, biology, medicine, political science, and communication sciences may benefit from the course.
A maximum of 80 participants will be allowed in this course.
Please note that the selection for this course will be done on a first-come-first-served basis. Also note that there is always a one-day delay between the registration system and the information on the website about the availability of places.
For an overview of all our summer school courses offered by the Department of Methodology and Statistics please click here.
Aim of the course
The main objective of the course is to acquire a basic understanding of how to use Mplus for SEM as applied in the social and behavioral sciences. Moreover, participants will learn how to analyse datasets with Mplus, to interpret the output and to report the results.
Learning goals per day:
- Learning the diagramming conventions of SEM used in the literature.
- Getting familiarized with the Mplus user interface.
- Learning Mplus defaults for data structures and input files along with tips and tricks for understanding error messages and tech output.
- Gain an understanding of degrees of freedom in a model and how Mplus treats different parameters.
- Understand how to interpret current model fit information provided by the software along with comparing models.
- Getting hands-on experience with Mplus by reading in data, creating an input file, analyzing example data, and experimenting with defaults to help understand the dynamics of Mplus.
- General overview of Exploratory and Confirmatory Factor Analysis.
- Learn about multiple group models in Mplus.
- Discussion of measurement invariance and how to evaluate it.
- Learn how to fit factor analytic models in Mplus using different methods of scale setting and how these methods influence interpretations of results.
- Applying these techniques to example data and practice interpreting the results
- Gaining an understanding of how to apply these techniques to your own research and data
- Learn the connection between path diagrams and the simple linear regression equations.
- Understand the path tracing rules.
- Learn how path analysis can be used for investigation of moderation and mediation.
- Learn how factor analysis and path analysis are combined for full structural equation modeling.
- Learn, and get hands-on experience with two popular longitudinal SEM models for assessing relations between variables over time, i.e., the cross-lagged panel model (CLPM) and random intercept cross-lagged panel model (RI-CLPM).
- Gain understanding of some conceptual and statistical concerns with regards to these models---specifically, the topic of trait-like stability, measurement timing and the lag-problem, and measurement error---and how these concerns can be addressed.
- Apply learned methods to your own data
- individual consultation
Four to five full days.
Day 1: The morning session consists of lectures. In the afternoon session, participants obtain hands-on Mplus experience with the discussed topics and models during a computer lab.
Days 2-4: Both the morning and afternoon sessions consist of lectures followed by a computer lab where everyone can practice working with Mplus.
Day 5 (optional): Both the morning and afternoon sessions consist of individual consultations with Mplus experts and room to work on your own data. In the morning, we also provide some Q&A sessions for some of the learned topics
The tuition fee for PhD students from the Faculty of Social and Behavioural Sciences from Utrecht University will be funded by the Graduate School of Social and Behavioural Sciences.
Utrecht Summer School does not offer scholarships for this course.
The housing costs include housing, plus a Utrecht Summer School sleeping bag, for you to keep. This sleeping bag also includes an inflatable pillow and matrass cover. If you wish to bring your own bedding, please contact us, so we can give you a 50 EUR discount on the housing fee. Please note that you cannot buy individual bedding items.
Team M&S Summer school | E: firstname.lastname@example.org