University of Gothenburg
Två Rubiks kub staplade på varandra
Photo: Olav Ahrens Rotne

Methods for causal inference in educational research, 7.5 credits

The course give a broad introduction to methods for causal inferences and is organised in four parts.

In the first part of the course the distinction between causal and non-causal research questions is introduced, and the reasons why it is generally impossible to answer causal questions through analyzing associations among observed variables are made explicit.

In the second part of the course three frequently used approaches for answering causal questions are treated in some detail, namely regression-discontinuity (RD) designs, IV regression analysis and fixed-effects/difference-in-differences. The logic upon which these approaches is based is presented, and the use and interpretation of the techniques is illustrated with both simulated and real data in the R system.

In the third part of the course structural equation modelling and propensity score matching are presented as methods which use conditioning on observed and latent variables to prevent bias in estimates of causal effects.

The fourth and final part of the course demonstrates how RD and IV designs may be combined, and how IV models may be estimated with SEM techniques.

Entry requirements

Knowledge equivalent to the learning goals in QRMs courses  Regression analysis in educational research (QRM1802) and Structural equation modelling in educational research (QRM1806).

Practical information

Course code

Course start
Spring 2022: April 11

Application period
Oct 1 - Feb 15

Campus days
Spring 2022: Dates and place will be decided later

Syllabus QRM1809

Reading list QRM1809