Partial Identification of Dose Responses with Hidden Confounders

TL;DR

This paper introduces a novel method to bound causal effects of continuous treatments in observational data when hidden confounders exist, providing tighter estimates than existing models and demonstrating practical application.

Contribution

The paper develops a new sensitivity analysis technique for continuous treatments that accounts for hidden confounders, improving bounds on causal effects compared to prior methods.

Findings

Our method yields tighter bounds on dose-response curves.

It outperforms existing continuous sensitivity models in benchmarks.

Applied to real data, it reveals meaningful dose-dependent causal effects.

Abstract

Inferring causal effects of continuous-valued treatments from observational data is a crucial task promising to better inform policy- and decision-makers. A critical assumption needed to identify these effects is that all confounding variables -- causal parents of both the treatment and the outcome -- are included as covariates. Unfortunately, given observational data alone, we cannot know with certainty that this criterion is satisfied. Sensitivity analyses provide principled ways to give bounds on causal estimates when confounding variables are hidden. While much attention is focused on sensitivity analyses for discrete-valued treatments, much less is paid to continuous-valued treatments. We present novel methodology to bound both average and conditional average continuous-valued treatment-effect estimates when they cannot be point identified due to hidden confounding. A semi-synthetic benchmark on multiple datasets shows our method giving tighter coverage of the true dose-response curve than a recently proposed continuous sensitivity model and baselines. Finally, we apply our method to a real-world observational case study to demonstrate the value of identifying dose-dependent causal effects.