Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 422 - Recent Development of Machine Learning Methods in Causal Inference
Type: Invited
Date/Time: Thursday, August 12, 2021 : 4:00 PM to 5:50 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #314463
Title: Almost Matching Exactly
Author(s): Cynthia Rudin and Alexander Volfovsky* and Sudeepa Roy
Companies: Duke University and Duke University and Duke University
Keywords: causal inference; interpretability; machine learning
Abstract:

I will present a matching framework for causal inference in the potential outcomes setting called Almost Matching Exactly. This framework has several important elements: (1) It creates matched groups that are interpretable. The goal is to match treatment and control units on as many covariates as possible. (2) It creates accurate estimates of individual treatment effects. This is because we use machine learning on a separate training set to learn which features are important for matching. The key constraint is that units are always matched on a set of covariates that together can predict the outcome well. (3) It is fast and scalable. It scales to datasets that are so large that they do not fit in main memory, owing to techniques from the field of databases. Its run-time on a single processor is also fast, owing to efficient bit-vector computations. In summary, these methods rival black box machine learning methods in their estimation accuracy but have the benefit of being interpretable and easier to troubleshoot. Our lab website is here: https://almostmatchingexactly.github.io


Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program