Final Part 3: A Selected History of Quantitative Causal Inference
The Extraordinary Role of Data Workers and Data Theorists at Princeton and Harvard
In the previous part 1 in this series, I discussed the rise of the potential outcomes model with Neyman, the realization that physical randomization solved the fundamental problem of causal inference from Fisher. In Part 2, I discussed the role that Princeton’s Industrial Relations Section had in shifts made within empirical microeconomics by highlighting complex problems in analyzing job trainings programs, calling for explicit randomization, and the introduction of new research designs focused on treatment assignment like the difference-in-differences design. I noted at length the importance of Orley Ashenfelter in creating the culture and ethos of the Section, along with David Card and others, that drove hard the point that empirical labor practices were flawed and that they would carve out a new path forward. In this final part, I will discuss what happens when Josh Angrist, a graduate of Princeton, goes to Harvard and meets Guido Imbens and Don Rubin and works on a landmark stu…
Keep reading with a 7-day free trial
Subscribe to Scott's Substack to keep reading this post and get 7 days of free access to the full post archives.