Double Robust, Flexible Adjustment Methods for Causal Inference: An Overview and an Evaluation

• Main Author: Hoffmann, Nathan Isaac
• Other Authors: Hazlett, Chad
• Format: Thesis
• Language: English
• Published: eScholarship, University of California 2024
• Subjects: Statistics; causal inference; double robust; machine learning; DML
• Online Access: https://escholarship.org/uc/item/4xf0n55v

This thesis is a guide to some of the latest methods in double robust, flexible covariate adjustment for causal inference, and it compares these methods to more traditional statistical methods and flexible "single robust"' methods. It does this by using both simulated data where the treatment effect estimate is known, and then using comparisons of experimental and observational data from the National Supported Work Demonstration. Methods covered include Augmented Inverse Probability Weighting (AIPW), Targeted Maximum Likelihood Estimation (TMLE), and Double/Debiased Machine Learning (DML). Results suggest that some of these methods do outperform traditional methods in a wide range of simulations, but only slightly. In particular, the top performers are TMLE and AIPW in conjunction with flexible machine learning algorithms. But G-computation with the same flexible machine learning algorithms obtains almost identical results, and simple regression methods are nearly comparable in bias and are much more computationally efficient.