The main goal of research is to explain phenomena. However, the observed data only provides us with correlations between variables, while researchers' interest most often is to identify causal relationships, in order to be able to implement policies or actions and have an influence on the elements. In order to estimate properly causal effects when we work with non experimental data (e.g. survey data), it is necessary to control for all possible spurious effects. Structural Equation Modelling is a very useful tool in this context, also because it allows differentiating between latent and observed variables. In this course, we will first introduce the general problem of causality. Then, we will focus on the framework of non-experimental data and see how we can use SEM to estimate causal effects. We will introduce LISREL, as one potential program to deal with these kinds of models. The course will both include lectures and applied sessions in which the respondents will have to work on examples and try out the methods explained during the lectures.No previous knowledge is needed, but familiarity with equations, correlations or regressions is preferable. Being able to get a correlation matrix from software like SPSS would also be useful.The software LISREL will be used.

Course leader
Melanie Revilla

Target group
Students, researchers, business professionals who need to develop good quality surveys and/or need to apply appropriate and up-to-date statistical methods.

Fee info
EUR 150: Student rate EUR 300: Academic rate (teachers & researchers)

Universitat Pompeu Fabra
Address: Department of Political and Social Sciences, Carrer Ramon Trias Fargas, 25-27 Campus Ciutadella
Postal code: 08005
City: Barcelona
Country: Spain
Website: http://www.upf.edu/survey/Summer/
E-mail: recsm@upf.edu
Phone: +3493 542 20 00