The primary objective of this course is to train students in causal inference analysis, i.e., techniques for identifying the cause-and-effect relationship between events. This is typically done by comparing the results of an intervention/policy/shock on a group of people (called treated) with a control group that does not receive the intervention/shock.
Two techniques are going to be studied here:
- Difference-in-differences
- Regression Discontinuity Design
In each case, examples applied to energy and environmental issues are going to illustrate the scientific usefulness of these techniques.
This course will help students to develop a number of important skills, including:
Understanding the concept of cause and effect and how it applies to the study of real-world phenomena.
The ability to use statistical software to analyze data and test hypotheses about causal relationships (Python for all and STATA and R in addition for economists).
The ability to critically evaluate the assumptions and limitations of different causal inference methods and apply them appropriately to different research questions.
Lecture 1: The basis (OLS and its assumptions)
Lecture 2: Panel analysis (Pooled, between and within estimators)
Lecture 3: Causal Inference (intro, RCT)
Lecture 4: Difference-in-differences
Lecture 5: Regression discontinuity design
All the slides are in English. If students really have the prerequisites, the course is also taught in English, if not in French to be as informative as possible.
- Irakaslea: Fabien Candau