You are here:

Structural Equation Modelling

Date:

01/04/2019

Organised by:

University of Kent

Presenter:

Professor George Chryssochoidis.

Level:

Entry (no or almost no prior knowledge)

Contact:

Nikki Gregory, N.C.Gregory@kent.ac.uk

Map:

View in Google Maps  (CT2 7NZ)

Venue:

Giles Ln, Canterbury

Description:

Description:

Structural Equation Modeling (SEM) is a statistical methodology that brings together psychometrics and econometrics is widely widely used in social sciences. Regarding psychometrics, SEM allows for latent variables with multiple indicators primarily regarding measurement. Regarding econometrics, SEM allows for multiple equations, and that allows identifying structural links between variables. In today’s SEM software (such as Mplus, EQs, AMOS, Lisrel, R), the models are so flexible that they encompass most of the statistical methods that are currently used in social sciences.

With SEM You Can:

  • Measure your variables better and do so with few or multiple indicators and adjust for measurement error in predictor as well as dependent variables.
  • Test / Infer causality.
  • Estimate simultaneously many equations together.
  • Represent your theory with diagrams too.
  • Investigate mediation and moderation.
  • Estimate and compare models across multiple groups of individuals/sectors/countries
  • And Many Other!

Overall, the training concentrates on developing modelling reasoning and demonstrate best practice in tackling modelling of social science research topics using SEM. 
It clarifies the scope and limits of SEM modelling as well as its usefulness. Topics may include

1) Introducing SEM and theory development/testing
2) The SEM language and thinking
3) Working with Latent Variables: Confirmatory and Other Types of Factor Analysis for SEM. 
4) How to Conduct Regression, and Path Analysis (Multiple Simultaneous Equations). 
5) Multilevel Modeling, Latent Growth Modeling, Dynamic SEM

This workshop will use the software package R: participants do not need any prior knowledge of R for the workshop.

Trainer: Professor George Chryssochoidis.

Cost:

Free to Kent postgraduates (and Kent staff) and Free to PGRs in Kent doctoral training partnership institutions,*

£30 for all other PGRs

£60 for other researchers: (non-Kent staff, alumni, charity, not for profit organisations)

£90 for commercial participants.

Website and registration:

Region:

South East

Keywords:

Qualitative Data Handling and Data Analysis, Latent Variable Models, Structural equation models

Related publications and presentations:

Qualitative Data Handling and Data Analysis
Latent Variable Models
Structural equation models

Back to archive...