Structural Equation Modelling Workshop
Date and Venue:
Monday 17th Feb: International Building PC Lab 1 (IN005) - 10am to 5pm
Tuesday 18th Feb: HITT Lab, through the Horton Building - 10am to 5pm
Wednesday 19th Feb: HITT Lab, through the Horton Building - 10am to 5pm
The CSS will be running a three day workshop on structural Equation Models (SEM).
SEMs are statistical models, used primarily to evaluate whether theoretical models are plausible when compared to observed data. SEMs are very general and are used in many Social Science disciplines. They are frequently used to analyse survey data and the structure of attitudes and values.
The objectives of this course are to show how confirmatory factor analysis and structural equation modelling can be used to develop and/or test both measurement models and causal theories with latent variables especially for cross cultural comparisons.
This course provides a practical introduction into how causal theory can be translated into a structural equation model, and how the model can be estimated and tested using SPSS and Amos. The course assumes some background knowledge in quantitative analysis and linear regression.
In the first part, we will offer a brief theoretical introduction to SEM and the most important aspects of them (for example, model fit).
We will also deal with confirmatory factor analysis (CFA) relating single or multiple indicators to one (CFA) or several latent variables (Simultaneous Confirmatory Factor Analysis). Different specifications of measurement models are tested via CFA as a special case of a SEM. Special emphasis is given to the cross cultural analysis of multiple groups (MGCFA) for comparisons within and between societies including intercepts of observed variables and latent means.
The second part comprises both the structural model and the measurement model. Topics include recursive vs. non-recursive models for the structural part of the model, moderation (Interaction effects), mediation (covering the causal steps approach, product of coefficients, and bootstrapping techniques), as well as moderated mediations (once again, with an eye on multigroup comparisons).
Special emphasis is directed toward the use of the multiple-group option, for cross-national comparisons of both the measurement and the structural model. A major focus will be the process of model modification and alternative model testing using adequate fit measures and how to report CFA and SEM results. All examples are based on data from the European Social Survey (ESS) .
This course is open to staff and research students at Royal Holloway. Places are limited. To register for the course please contact Oliver Heath (email@example.com).
Elementary statistical knowledge of SPSS and linear regression is assumed. No other prior knowledge is assumed, but the course aims to provide a grounding in the theory and practicalities of using SEMS, so will be most suitable for those who intend to use and apply CFA and SEM in their own research.