Causal Inference for Functional Treatments with Stochastic Policies

2026-06-25

AI Summary

This study addresses causal inference for continuous-time interventions—such as three-hour physical activity patterns—on mortality when conventional positivity assumptions fail and time-dependent confounding is present. The authors propose a stochastic policy-based functional intervention framework that adjusts the intervention distribution via a single analyst-specified basis function, thereby defining an identifiable causal estimand without requiring positivity. By integrating functional regression with doubly robust estimation, the method effectively controls for time-varying confounders. Theoretical analysis establishes that the resulting estimator possesses rate double robustness and asymptotic normality. Empirical application to NHANES data demonstrates the feasibility and statistical efficiency of the proposed approach.

Abstract

Wearable devices can accurately measure human behavior, providing a unique opportunity to understand how behavior impacts health. Recent studies leveraging functional regression methods have found a strong relationship between accelerometer-collected physical activity and mortality. However, to determine if physical activity patterns impact mortality it is necessary to understand the causal effects of policies for physical activity, i.e., a function-valued treatment. Functional treatments present several challenges for causal effect estimation: 1) defining a scientifically meaningful estimand that reflects real-world policies and satisfies positivity is nontrivial; and 2) the potential for temporal confounding over continuous time. To address these, we propose stochastic policies for functional treatments that allow estimation of causal effects of changing the treatment distribution without requiring a positivity assumption. We develop a novel method for such that modifies the treatment through a single basis function chosen by the analyst, allowing for clear control over treatment modification and temporal confounding feedback. We show asymptotic normality of our estimators and that they exhibit rate double robustness. We apply our methods to the National Health and Nutrition Examination Survey to determine the causal effect of increasing physical activity over three-hour periods on mortality.

Problem

• functional treatments
• causal inference
• stochastic policies
• temporal confounding
• positivity

Innovation

• stochastic policies
• functional treatments
• causal inference
• temporal confounding
• double robustness