Course Description
A key challenge in public policy is determining whether policies and interventions have a measurable impact on living standards and measures of well-being. What are the impacts of programs and initiatives that have been implemented, or at least piloted on a small scale? For example, the impact of conditional cash transfers on education, health and well-being of children, or the impact of financial literacy training on the ability of households to manage their finances? Over the past decade, a large literature has emerged to attempt to answer these important questions.
This course exposes the students to key concepts and quantitative tools in impact evaluation. It will draw examples from studies and evaluations that have been conducted around the world in recent years. It will introduce students to experimental and quasi-experimental approaches that have been used in impact evaluation. Students will use Stata to analyze microeconomic data and apply various quantitative approaches. The empirical exercises include both in-class exercises and problem sets.
Specific Learning Goals
Clear understanding of causal identification: what it is, what it isn’t, and why it matters
How to achieve causal identification: what are the key methods and how to apply them.
Including both experimental and quasi-experimental approaches
Including familiarity with recent examples of applications
Including hands-on skills in applying each method using Stata
What are the pros and cons of each method: what are the data requirements, what are the underlying assumptions, under which conditions are the assumptions reasonable, which is the best method for a given context?
Potential Outcomes Framework
Power calculations
Design & Challenges
Statistical Inference
Ethics & Transparency
Instrumental Variables
Regression Discontinuity
Panel Data & Fixed Effects
Difference in Differences
Advanced DiD & Event Study
Cunningham (2021). Causal Inference the Mixtape. Yale: New Haven.
Glennerster and Takavarasha. (2013) Running Randomized Evaluations. Princeton, NJ: Princeton.
Christensen, Freese, and Miguel. (2019). Transparent and Reproducible Social Science Research. Oakland, CA: University of California Press.
Djimeu and Houndolo. (2016) “Power calculation for causal inference in social science: Sample size and minimum detectible effect determination” 3ie Working paper 26.
Anderson (2008) “Multiple Inference and Gender Differences in the Effects of Early Intervention“ Journal of the American Statistical Association. 103(484): 1481-1495
de Chaisemartin and d'Hautfoeuille (2020) "Two-way fixed effects estimators with heterogeneous treatment effects" American Economic Review. 110(9): 2964-2996
Belissa, Bulte, Cecchi, Gangopadhyay, and Lensink. (2019) “Liquidity constraints, informal institutions, and the adoption of weather insurance: A randomized controlled Trial in Ethiopia” Journal of Development Economics. 140: 269-278.
Gine and Mansuri. (2018) “Together We Will: Experimental Evidence on Female Voting Behavior in Pakistan” American Economic Journal: Applied Economics. 10(1):207-35
Miguel, Satyanath, and Sergenti. 2014. “Economic shocks and civil conflict: An instrumental variables approach” Journal of Political Economy, 112(4):725-753.
Lucas and Mbiti. (2014) “Effects of school quality on student achievement: discontinuity evidence from Kenya” American Economic Journal: Applied Economics. 6(3): 234-263.
Card and Krueger (1994). “Minimum Wages and Employment: A Case Study of the Fast-Food Industry in New Jersey and Pennsylvania” The American Economic Review. 84(4) 772-793.
Duflo. (2001) “Schooling and labor market consequences of school construction in Indonesia” American Economic Review. 91(4): 795-813.
Workflow basics (Anders Sundell)
Basic commands and shortcuts (Tobias Pfaff, 2009)
Printable Stata cheat sheets (Geocenter)
More complete tutorial (Oscar Torres-Reyna)