Courses in Applied Social Surveys (CASS)

Structural Equation Modelling for Cross-Sectional and Panel Data

Venue: Highfield Campus, University of Southampton, UK
Presenter: Patrick Sturgis and Katy Sindall
Dates of Course: Wednesday 22nd - Friday 24th May 2013

This course has already run. Please check the course listings for a future course.

Summary of Course:

This course starts by introducing the principles and foundational ideas of structural equation modelling, in particular for cross-sectional data, before focusing on the use of these models to analyse panel data. Topics will include: simplex models; cross-lagged panel models, latent curve analysis, multiple group models, growth mixture models and parallel process models.

Course Objectives:

Course Content:

This course will include the following topics:

The methods will be illustrated and compared using analyses of attitudes collected in the British Household Panel Survey and the British Election Panel Survey. The course will have a strong practical emphasis, with regular computing sessions enabling participants to work through examples using commercially available software. The main software to be used during the course is Amos.

Target Audience:

The course is aimed at researchers, especially those in the social, economic, educational and medical sciences, who wish to familiarise themselves with structural equation modelling, particularly with the aim of analysing panel survey data. Participants should already be familiar with basic statistical theory, including inference and multiple linear regression, and should have some knowledge of longitudinal data analysis.

Pre-requisites:

Participants on this course should have prior statistical knowledge of probability theory, the principles of statistical inference, and linear regression (up to the level of the CASS Survey Data Analysis II course). Familiarity with longitudinal data analysis would be an advantage, though not a prerequisite. No prior knowledge of structural equation modelling software will be assumed.

Course Materials:

Participants will receive written course notes.

The Instructor:

Patrick Sturgis is a Professor at the Division of Social Statistics at the University of Southampton. He is also Director of the National Centre for Research Methods (NCRM). He has a BA in Psychology and an MSc and PhD in Social Psychology. One of his research interests is the use of structural equation models in the social sciences. He has many years experience of teaching short courses, particularly on structural equation modelling.

Katy Sindall is a Lecturer in Social Science Research Methods at the University of Southampton. She has previously worked as a researcher for both the Metropolitan Police and the Ministry of Justice. Her interests are in public opinion research, particularly concerning perceptions of the police and crime, and the application of advanced quantitative methods to explore such substantive areas. She has experience of teaching quantitative methods courses and short courses in structural equation modelling. 

Course Fee:

£30 per day for UK registered students. £60 per day for staff from UK academic institutions (including research centres), ESRC funded researchers and UK registered charitable organisations. £220 per day for all other participants. The course fee includes course materials, lunches and morning and afternoon refreshments. Travel and accommodation are to be arranged and paid for by the participant.

Location and Accommodation:

The course will be held at the Southampton Statistical Sciences Research Institute, Building 39, University of Southampton, Southampton, SO17 1BJ. Participants are left to make their own accommodation arrangements. Further information on local accommodation and course location is available here.

Duration:

This is a 3-day course. The course will begin with coffee and registration at 9.30am with formal teaching starting at 10.00am on the first day. It will finish at around 5.00pm on the last day.

Preparatory Reading:

For participants who wish to do background reading, the following references may be useful. Please note that although reading is optional, participants who have little statistical background on modelling panel data are strongly advised to look at some of these references.