Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions

TL;DR

This paper introduces a scalable method for sensitivity and uncertainty analysis in causal effect estimation of continuous interventions, addressing unobserved confounding in high-dimensional observational data.

Contribution

It develops a continuous treatment-effect marginal sensitivity model and scalable algorithms for bounds estimation under unobserved confounding, applicable to large datasets.

Findings

Derived bounds consistent with observed data and hidden confounding levels

Introduced scalable deep models for high-dimensional data

Applied to climate science, revealing impacts of unobserved confounders

Abstract

Estimating the effects of continuous-valued interventions from observational data is a critically important task for climate science, healthcare, and economics. Recent work focuses on designing neural network architectures and regularization functions to allow for scalable estimation of average and individual-level dose-response curves from high-dimensional, large-sample data. Such methodologies assume ignorability (observation of all confounding variables) and positivity (observation of all treatment levels for every covariate value describing a set of units), assumptions problematic in the continuous treatment regime. Scalable sensitivity and uncertainty analyses to understand the ignorance induced in causal estimates when these assumptions are relaxed are less studied. Here, we develop a continuous treatment-effect marginal sensitivity model (CMSM) and derive bounds that agree with the observed data and a researcher-defined level of hidden confounding. We introduce a scalable algorithm and uncertainty-aware deep models to derive and estimate these bounds for high-dimensional, large-sample observational data. We work in concert with climate scientists interested in the climatological impacts of human emissions on cloud properties using satellite observations from the past 15 years. This problem is known to be complicated by many unobserved confounders.