Difference-in-differences, Average Treatment Effects and the Importance of Mechanisms: Part 1
Ignaz Semmelweis reasoning out mechanisms through heterogeneity analysis and designed non-randomized experiments.
This substack was inspired by a lecture given by Pamela Jakeila on difference-in-differences and a random DM exchange with Andrew Goodman-Bacon that caused me to ruminate for weeks. All errors are my own as the ruminating is not done. I can’t claim that the following is coherent, only that I think something inside it is interesting to me if no one else. This is going to be the first part in a multi-part substack on causal inference and difference-in-differences, but in trying to do it in one, I couldn’t because I found the essay so enchanting.
My next series is a few things at once. It’s a reminder that sometimes people will do everything in their power to present evidence supporting scientific facts, be unpersuasive and be sent to a mental hospital by their best friend where they spend the next two weeks being beaten by guards mercilessly and then die. But it’s also a discussion of difference-in-differences, and perhaps the challenges of estimation if you’re not entirely clear wha…
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.