A Tutorial on Doubly Robust Learning for Causal Inference

TL;DR

This tutorial explains doubly robust learning for causal inference, simplifying its methodology and demonstrating practical implementation with the EconML package to make it accessible for researchers and practitioners.

Contribution

It provides an accessible introduction to doubly robust methods, including practical coding examples, to facilitate adoption in causal inference tasks.

Findings

Demonstrates doubly robust approach through simulated case studies

Provides practical coding examples with EconML package

Simplifies complex methodology for broader accessibility

Abstract

Doubly robust learning offers a robust framework for causal inference from observational data by integrating propensity score and outcome modeling. Despite its theoretical appeal, practical adoption remains limited due to perceived complexity and inaccessible software. This tutorial aims to demystify doubly robust methods and demonstrate their application using the EconML package. We provide an introduction to causal inference, discuss the principles of outcome modeling and propensity scores, and illustrate the doubly robust approach through simulated case studies. By simplifying the methodology and offering practical coding examples, we intend to make doubly robust learning accessible to researchers and practitioners in data science and statistics.