Double machine learning to estimate the effects of multiple treatments and their interactions

2025-05-19

AI Summary

This paper addresses the challenge of causal inference under multivalued treatments—binary, categorical, and continuous—as well as their interaction effects, a gap unaddressed by existing methods predominantly focused on binary interventions and neglecting concurrent, multiple treatments. We propose the first general-purpose framework based on double machine learning (DML), integrating Neyman orthogonality and cross-fitting to accommodate heterogeneous treatment types and complex confounding structures. The framework employs machine learning–driven propensity score and outcome models (e.g., random forests, Lasso). We establish asymptotic normality of the proposed estimator and derive a robust variance estimator. Extensive simulations demonstrate high accuracy and robustness across diverse data-generating processes. Empirically, we apply the method to a cohort of 2,455 HIV patients in Nigeria, providing the first quantitative assessment of the joint causal effect of three distinct treatments on HIV-associated nephropathy.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Multiagent Systems: Mechanism Design

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Causal inference literature has extensively focused on binary treatments, with relatively fewer methods developed for multi-valued treatments. In particular, methods for multiple simultaneously assigned treatments remain understudied despite their practical importance. This paper introduces two settings: (1) estimating the effects of multiple treatments of different types (binary, categorical, and continuous) and the effects of treatment interactions, and (2) estimating the average treatment effect across categories of multi-valued regimens. To obtain robust estimates for both settings, we propose a class of methods based on the Double Machine Learning (DML) framework. Our methods are well-suited for complex settings of multiple treatments/regimens, using machine learning to model confounding relationships while overcoming regularization and overfitting biases through Neyman orthogonality and cross-fitting. To our knowledge, this work is the first to apply machine learning for robust estimation of interaction effects in the presence of multiple treatments. We further establish the asymptotic distribution of our estimators and derive variance estimators for statistical inference. Extensive simulations demonstrate the performance of our methods. Finally, we apply the methods to study the effect of three treatments on HIV-associated kidney disease in an adult HIV cohort of 2455 participants in Nigeria.

Problem

• Estimating effects of multiple diverse treatments and interactions
• Developing robust methods for multi-valued treatment regimens
• Applying machine learning to overcome biases in causal inference

Innovation

• Double Machine Learning for multiple treatments
• Neyman orthogonality to reduce biases
• Estimating interaction effects robustly