« Back to all events

Causal Inference

Dates:
  • Tue 08 Jan 2019 16.00 - 18.00
  Add to Calendar 2019-01-08 16:00 2019-01-08 18:00 Europe/Paris Causal Inference

Either explicitly or implicitly, the goal of most empirical research is to interpret causally the co-occurrence of interesting phenomena. Addressing causality, however, has been notoriously difficult without the luxury of experimental data. This course will introduce you to an authoritative framework of causal inference in social sciences, i.e. the potential outcomes framework. This framework will be the basis to then examine in detail a set of methods that allow you to make convincing causal claims without working with experimental data. We
will look at three such designs:
1. Instrumental Variables;
2. Regression Discontinuity Design; and
3. Difference-in-Differences estimation.

We will also look at a fourth estimation method, which, similar to regression, assumes that selection is conditional on observables: Matching. It differs from regression in ways that make it valuable and helpful, as we will explain in the course.
For every method, the following structure will be employed: first, a running example from the literature will provide the motivation and intuition. We will then proceed with the formal identification derivation and finally we will focus on estimation strategies and robustness checks. For each method there will be a hands-on lab section, where we will apply these methods with real data. We will use both R and Stata throughout.

We will also delve into non-standard approaches to inference and we will specifically look at:
a) how to address the problem of clustering;
b) boostrapping techniques; and
c) randomization inference.

Finally, we will spend two hours on synthetic control methods. We will also look briefly at mediation analysis, trying to illustrate why it is more difficult than it seems at first sight. Specific examples and readings will be provided for this section.

Seminar Room 2, Badia Fiesolana DD/MM/YYYY
  Seminar Room 2, Badia Fiesolana

Either explicitly or implicitly, the goal of most empirical research is to interpret causally the co-occurrence of interesting phenomena. Addressing causality, however, has been notoriously difficult without the luxury of experimental data. This course will introduce you to an authoritative framework of causal inference in social sciences, i.e. the potential outcomes framework. This framework will be the basis to then examine in detail a set of methods that allow you to make convincing causal claims without working with experimental data. We
will look at three such designs:
1. Instrumental Variables;
2. Regression Discontinuity Design; and
3. Difference-in-Differences estimation.

We will also look at a fourth estimation method, which, similar to regression, assumes that selection is conditional on observables: Matching. It differs from regression in ways that make it valuable and helpful, as we will explain in the course.
For every method, the following structure will be employed: first, a running example from the literature will provide the motivation and intuition. We will then proceed with the formal identification derivation and finally we will focus on estimation strategies and robustness checks. For each method there will be a hands-on lab section, where we will apply these methods with real data. We will use both R and Stata throughout.

We will also delve into non-standard approaches to inference and we will specifically look at:
a) how to address the problem of clustering;
b) boostrapping techniques; and
c) randomization inference.

Finally, we will spend two hours on synthetic control methods. We will also look briefly at mediation analysis, trying to illustrate why it is more difficult than it seems at first sight. Specific examples and readings will be provided for this section.


Location:
Seminar Room 2, Badia Fiesolana

Affiliation:
Department of Political and Social Sciences

Type:
Seminar

Organiser:
Professor Elias Dinas (EUI - Department of Political and Social Sciences)

Contact:
Jennifer Rose Dari (EUI - Department of Political and Social Sciences) - Send a mail
 
 

Similar events

 

Page last updated on 18 August 2017