Led by Professor Alasdair Rutherford
In this session we will introduce the methods of Regression Discontinuity Design (RDD), and provide the opportunity to apply them in a practical lab using Stata.
Regression discontinuity design is a quasi-experimental pre-test and post-test method, that seeks to elicit causal effects. By examining observations that are lying closely on either side of the threshold it is possible to estimate ‘treatment effects’ in environments where experimentation using randomisation would not be feasible. RDD techniques are widely understood in areas such as econometrics, but have been used less frequently in other areas of social science.
The course will:
- Introduce the concept of discontinuity designs
- Outline the statistical theories that underpin regression discontinuity designs (RDD)
- Highlight how RDD can be used to test ideas and theories
- Showcase some examples of research questions and data that are suited to RDD
- Demonstrate how Stata can be used for RDD analyses
After the course, participants will:
- Understand the fundamental concepts associated with RDD
- Be able to interpret the result of RDD analysis
- Better understand which research questions and data that are suited to RDD
- Be able to apply RDD analyses in Stata
Participants should ideally be familiar with Stata software, although students familiar with using syntax in SPSS, R, Python or similar should be fine. Students should have a good knowledge of applied statistical analysis, especially regression models.
An awareness of causal methods would be an advantage, but is not essential.
Register for Summer School here!