This course is designed to cover the fundamental principles of Structural Equation Modeling (SEM) and introduce the AMOS and/or Mplus software packages to estimate structural equation models.
(N.B. Although the instructor will teach and use both packages throughout the course, students may choose to work with just one of the packages or they may choose to work with both.)
This course will be run over 3 days in three sessions per day:
- 10.00am - 11.30pm - session 1
- 12.00pm - 1.30pm - session 2
- 2.30pm - 4.00pm - Session 3
Your instructor will offer individual consultation sessions for 15 - 20 minutes for each participant by appointment.
Mr Philip Holmes-Smith (OAM) is the Director of School Research, Evaluation and Measurements Services (SREAMS), an independent educational research consultancy business. His research, evaluation and measurement interests lie in the areas of teacher effectiveness and school improvement, accountability models and benchmarking, improving the quality of teaching, using student performance data to inform teaching, and large-scale achievement testing programs. He is an experienced teacher of social science research methods and is a regular instructor at the ACSPRI programs. He also regularly teaches Structural Equation Modeling (SEM) and Multi-Level Analysis (MLA) at various universities around Australia.
Structural Equation Modelling (SEM) is used widely by researchers in a diverse array of fields to find and test complex relationships amongst observed variables that measure latent (unobserved) variables and amongst the latent variables themselves. SEM subsumes other analytical techniques (such as factor analysis, regression analysis and path analysis) into one omnibus approach to modeling relationships amongst observed and latent variables. This course is designed to introduce the basic concepts of SEM and to introduce the use of the AMOS and/or Mplus software packages to estimate SEM models.
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.
The target audience for this course is post graduate students, academic staff and other researchers needing to learn the basic concepts of SEM and how to run structural equation models using the AMOS and/or Mplus software packages.
Day 1
Part A: Introduction to Structural Equation Modelling (SEM) & SEM Software
We will answer the question “What is Structural Equation Modeling (SEM)?” and understand the reasons for conducting SEM. We will review SEM software packages and understand the data structures required to run AMOS and/or Mplus.
Part B: Review of Factor Analysis and Regression Analysis
Because SEM is a combination of Factor Analysis and Regression Analysis, we will revise Factor Analysis by using IBM SPSS to run an Exploratory Factor Analysis (EFA) and using AMOS and/or Mplus to run a Confirmatory Factor Analysis (CFA). We will also revise Regression Analysis by using IBM SPSS to run a simple regression model and using AMOS and/or Mplus to run a univariate multiple regression model. We will also learn to understand AMOS and/or Mplus output.
Day 2
Part A: Fundamentals of Structural Equation Modelling
We will learn the problems with conventional analytical techniques and how SEM overcomes them. We will learn the fundamental principles underlying structural equation modelling and track the history from path analysis to modern structural equation modelling before gaining an overview of the eight steps to structural equation modelling.
Part B: SEM Steps 1-4
We will learn the first four steps of conducting SEM, namely: SEM Step 1 - Model conceptualisation; SEM Step 2 - Path diagram construction; SEM Step 3 - Model specification; SEM Step 4 - Model Identification. We will finish day 2 practicing Path diagram construction and Model specification.
Day 3
Part A: SEM Step 5
In SEM Step 5 - Parameter Estimation we will learn what SEM software packages do to estimate model parameters. We will then use AMOS and/or Mplus to run a full structural equation model and interpret the AMOS and/or Mplus output.
Part B: SEM Steps 6-8
We will learn the last three steps of conducting SEM, namely: SEM Step 6 - Assessment of model fit; SEM Step 7 - Model re-specification; and SEM Step 8 - Model cross-validation.
Part C: Putting it all together
We will finish the course with either example models from participants and/or a model provided by the lecturer.
Training in this course will be in 3 x 1.5 hour sessions per day over Zoom.
Questions are encouraged.
Individual consultation sessions will be for 15 - 20 minutes for each participant by appointment.
Participants must have completed an introductory course in statistics (or have equivalent experience).
Familiarity with multiple regression and factor analysis is highly desirable, as is experience with a statistical data analysis package such as IBM SPSS, SAS or Stata. However, it is assumed that participants have had little or no experience with either AMOS or Mplus.
The instructor's bound, book length course notes will serve as the course text. These notes will be sent to you in advance.
Other references include:
- Arbuckle, James L. (1983-2022). IBM SPSS AMOS 29 User’s Guide. IBM Corp.
- Muthén, L.K. and Muthén, B.O. (1998-2017). Mplus User’s Guide. Eighth Edition. Los Angeles, CA: Muthén & Muthén.
- Byrne, Barbara M. (2016). Structural Equation Modeling with AMOS: Basic Concepts, Applications, and Programming. (3rd Ed.) New York: Routledge Academic.
- Byrne, Barbara M. (2012). Structural Equation Modeling with Mplus: Basic Concepts, Applications, and Programming. New York: Routledge Academic.
- Kline, Rex B. (2023). Principles and Practice of Structural Equation Modeling (5th Ed.). New York: Guilford Press.
Q: Do I have to have any prerequisites to do this course?
A: Yes, see recommended background section for details.
The course I take is mainly on Structural Equation Modelling and how to use SPSS AMOS and I feel it is really helpful. Phil has given us really good practices and clear explanation.
The course was extremely useful and I would recommend it to anyone interested in SEM
The course content was relevant and useful for my research. Phil did an excellent job in reviewing simple concepts first and then introducing more complex material to the course in a systematic way.
I found the online learning great. I know it can be difficult as a teacher this way (I've also had to teach online this year), but as a student I really liked it. The manual was good and the instructor managed the online environment well. It was great being in my own home for the week rather than needing to travel. I would enrol for online learning again, especially if I was confident in the quality of the training provider (ACSPRI have a good reputation in the field anyway, so I think you are well placed to make the switch).
I got a lot more out of this course than I had expected. I entered the course thinking I would be getting a new skill out of it, but even by lunchtime on the Monday, I was applying the concepts to my own data and realising how useful SEM will be in my work.
The theory and concepts were clearly explained including with examples then we got on the computers and learned ”how”. It was brilliant.
Yes I am ready to use this tool now. I am confident I can use it and solve problems.
The instructor's bound, book length course notes will serve as the course texts.
These will be posted to your nominated 'shipping address'.