Structural equation modelling (SEM) is used widely by researchers in a diverse array of fields to find and test complex relationships amongst observed (measured) variables and latent (unobserved) variables and amongst the latent variables themselves.
This course is designed as an applied introduction to the use of the AMOS software for estimating structural equation models. SEM subsumes other analytical techniques such as regression, path analysis, factor analysis, and canonical correlation. Detailed notes with worked examples and references will be provided as a basis for both the lecture and hands-on computing aspect of the course.
You will learn the underlying principles of Structural Equation Modelling, fundamental issues related to various, general, SEM models with continuous level data. The course focuses on the use of the AMOS program to diagram, test, and interpret the output for key, general, models including path models and latent variable models.
The target audience for this course is postgraduate students and academic staff with a sound understanding of multivariate statistics using continuous level data, who are looking to gain greater knowledge and expertise in SEM and the AMOS program.
Day 1
Fundamentals of SEM. Topics include a revision of factor analysis and regression analysis and their relevance to SEM; the advantages of SEM over conventional analytical techniques; the fundamentals underlying SEM; path diagrams, model specification and notation for structural equation models; model identification; parameter estimation; assessing model fit; model re-specification and model cross-validation. Throughout this part of the course participants will be introduced to the AMOS software with a particular emphasis on the Amos Graphics, including how to run models and how to review output. Considerable time is devoted to learning the graphical interface in the first day.
Day 2
Basic Models. This part of the course looks at the three basic types of structural equation models, namely: models for directly observed variables (regression and path analysis); measurement models with reflective indicators, confirmatory factor analysis (CFA) and higher-order CFA; and full structural models with latent variables including models with mediating variables.
Day 3
Common Problems in SEM. This part of the course explores issues with problem data and models including topics such as missing data, small samples, non-normal data, unidentified and inadmissible models. Models tested in this course assume continuous level variables and does not cover the treatment of non-continuous level data.
Day 4
Introduction to Advanced Topics. This part of the course gives an very brief introduction to the topics covered in the Advanced SEM courses including the testing of model and parameter invariance across groups (multi-group analysis), tests of indirect effects using bootstrapping, and latent growth models. This part is to demonstrate additional models that can be tested with the AMOS package rather than providing in-depth instruction in such advanced procedures.
Day 5
Personal Research. Finally, the course provides an opportunity for you to work on your own research problems. You are encouraged to bring a data set and/or research problem with you.
This course will take place in a computer lab. All equipment will be supplied including the course notes and example datasets.
You must have completed a university level course in multivariate statistics or have equivalent experience. Familiarity with multiple regression and factor analysis and experience with a statistical data analysis package such as SPSS, SAS or Stata is assumed. We no not expect you to have had any experience with AMOS although some understanding of the purpose of SEM is strongly recommended. Those students with no exposure to the purpose and use of SEM are encouraged to first complete the course Fundamentals of Structural Equation Modelling.
Suggested:
• Byrne, B. M. (2010). Structural Equation Modeling with AMOS: Basic concepts, applications and programming (2nd ed.). New York: Routledge.
Q: Do I have to have any prerequisites to do this course?
A: Yes, see recommended background section for details.
Really good balance of theory & explanation and practical application & exercise on the computer. (Winter 2014)
The content & delivery was very practical & applied. Very useful! (Winter 2014)
Excellent blend of instruction and practice. The many examples and opportunities to use the software consolidated skills (Summer 2015)
Effectively gained new skills, knowledge and understanding (Summer 2015)
It helped show how another teach instructs; it also consolidated my knowledge in the area which will support my own teaching. (Summer 2015)
I acquired the applied skills I needed to do my data analysis for my PHD research. (Winter 2015)
The instructor's bound, book length course notes will serve as the course texts.