An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

TL;DR

This paper proposes a unifying framework that leverages outcome-invariant data augmentation to improve causal effect estimation, especially in the presence of unobserved confounders, by connecting it with instrumental variable techniques.

Contribution

It introduces IV-like regression for bias reduction and demonstrates how parameterized data augmentation can simulate worst-case scenarios to enhance causal inference.

Findings

Regularized IV-based estimators reduce confounding bias.

Parameterized DA can simulate worst-case interventions.

The approach improves causal estimation in both theoretical and real data experiments.

Abstract

The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifying framework with topics in causal inference to make a case for the use of DA beyond just the i.i.d. setting, but for generalization across interventions as well. Specifically, we argue that when the outcome generating mechanism is invariant to our choice of DA, then such augmentations can effectively be thought of as interventions on the treatment generating mechanism itself. This can potentially help to reduce bias in causal effect estimation arising from hidden confounders. In the presence of such unobserved confounding we typically make use of instrumental variables (IVs) -- sources of treatment randomization that are conditionally independent of the outcome. However, IVs may not be as readily available as DA for many applications, which is the main motivation behind this work. By appropriately regularizing IV based estimators, we introduce the concept of IV-like (IVL) regression for mitigating confounding bias and improving predictive performance across interventions even when certain IV properties are relaxed. Finally, we cast parameterized DA as an IVL regression problem and show that when used in composition can simulate a worst-case application of such DA, further improving performance on causal estimation and generalization tasks beyond what simple DA may offer. This is shown both theoretically for the population case and via simulation experiments for the finite sample case using a simple linear example. We also present real data experiments to support our case.