Prediction-powered Generalization of Causal Inferences

TL;DR

This paper introduces prediction-powered algorithms for generalizing causal inferences from RCTs to target populations using observational data, addressing challenges of limited trial size and unmeasured confounding.

Contribution

It proposes novel methods that combine trial data with observational studies without assumptions, improving generalization robustness and accuracy.

Findings

Algorithms outperform existing methods in simulations.

High-quality observational data enhances generalization.

Robustness to unmeasured confounding is demonstrated.

Abstract

Causal inferences from a randomized controlled trial (RCT) may not pertain to a target population where some effect modifiers have a different distribution. Prior work studies generalizing the results of a trial to a target population with no outcome but covariate data available. We show how the limited size of trials makes generalization a statistically infeasible task, as it requires estimating complex nuisance functions. We develop generalization algorithms that supplement the trial data with a prediction model learned from an additional observational study (OS), without making any assumptions on the OS. We theoretically and empirically show that our methods facilitate better generalization when the OS is high-quality, and remain robust when it is not, and e.g., have unmeasured confounding.