Module description
This module covers the main empirical methods used for causal inference in economics, political economy, political science and development: randomised controlled trials, natural experiments, instrumental variables and regression discontinuity design. Students will learn how to use these methods to address important questions in the social sciences.
The emphasis is on applications and not on the derivation of estimators. This module follows the model of ‘learning by example’, and so we study a large number of articles published in leading journals in economics and political science. We consider the research question these articles address, how they address it, what data they use and the strength and weaknesses of their approach.
Each seminar is organized around one research article that students are asked to read in advance. The seminar will revolve around a critical discussion of this one article. By the end of the semester students will be able to read, understand and assess recent research articles published in leading academic journals.
Assessment details
2-hour written exam (60%) & 1,000-word essay (40%)
Educational aims & objectives
Students will be:
- Introduced to four of the most widely used empirical methods in economics, political economy and political science.
- Equipped with the skills to read and understand empirical papers in economics, political economy and political science.
- Enabled to formulate their own empirical studies – including data collection, the empirical specification and its implementation.
- Guided in interpreting empirical results and how these results can inform existing theories in economics, political economy and political science.
Learning outcomes
By the end of the course the students will be able to:
- read and engage critically with empirical papers in political economy, public policy, and economics and political science more generally.
- formulate research questions in a way that allows for empirical analysis
- collect their own data, become aware of how to deal with the lack of adequate data, carry on their own empirical analysis and interpret their results;
- formulate empirical research proposals that could be the starting point for an empirical dissertation in political economy.
Teaching pattern
Lecture Schedule [indicative]
1. Introduction to the potential outcomes framework. Example: career choices
2. Introduction to randomised controlled trials. Example: women as policy markers
3. Problems with randomised controlled trials. Example: health insurance
4. Natural Experiments. Example: John Snow and cholera
5. Natural Experiments. Examples: impact of taxation, minimum wages, incidence of UK housing benefit
6. Natural experiments. Examples: Do leaders matter? Climate shocks and exports. Who pays the sales tax?
7. Review of instrumental variables. Examples: The impact of dams on development. Colonialism and income.
8. Instrumental variables. Examples: The long-run impact of the Vietnam war. Income and democracy.
9. Regression discontinuity design. Examples: Incumbency advantage in the US House of Representatives.
10. Regression discontinuity design. Examples: Coercive labour market institutions.
Suggested reading list
Key Readings
Angrist, Joshua and Joern-Steffen Pischke, 2009. Mostly Harmless Econometrics, Princeton University Press.
Freedman, David, 2009. Statistical Models: Theory and Practice, published by Cambridge University Press.
Stock, James and Mark Watson, 2012. Introduction to Econometrics, Pearson Education.
Wooldridge, Jeffrey, 2003. Introductory Econometrics: A Modern Approach, South-Western College Publishing.