Causal Machine Learning & Experiments

Speakers:

• Sam Fuller; Postdoctoral Fellow at the Center for American Political Studies, Harvard University
• Jack T. Rametta; PhD Candidate in Political Science at the University of California, Davis

This talk will discuss our research agenda, broadly, and one of our working papers: “The balance permutation test: A machine learning replacement for balance tests.” This paper introduces a new machine learning method, with an accompanying R package, that can detect and address randomization issues in experiments. We show that the balance permutation test is able to detect complex imbalance in real, simulated, and even fabricated data.

This paper is the first in a series of projects leveraging machine learning for experimental applications. We’re interested in getting feedback and ideas on this paper, but we’re especially interested in thoughts about ongoing and future projects.