Nonparametric Heterogeneous Long-term Causal Effect Estimation via Data Combination

2025-02-26

AI Summary

Existing methods lack robust and efficient estimation of heterogeneous long-term causal effects. Method: This paper proposes the first nonparametric two-stage estimation framework that jointly leverages short-term experimental and long-term observational data. It introduces three novel nonparametric estimators—propensity-score–based, regression-based, and multiply robust—integrated with double-robust inference, kernel regression, and data-combination modeling. Contribution/Results: Under mild regularity conditions, we establish their asymptotic optimality and derive precise conditions under which they dominate existing alternatives. The framework balances theoretical rigor with computational feasibility. Extensive evaluations on multiple semi-synthetic and real-world datasets demonstrate substantial improvements over state-of-the-art methods, empirically validating the derived convergence rates and capacity to identify heterogeneous treatment effects. This work provides a principled new tool for policy evaluation and personalized intervention design.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Long-term causal inference has drawn increasing attention in many scientific domains. Existing methods mainly focus on estimating average long-term causal effects by combining long-term observational data and short-term experimental data. However, it is still understudied how to robustly and effectively estimate heterogeneous long-term causal effects, significantly limiting practical applications. In this paper, we propose several two-stage style nonparametric estimators for heterogeneous long-term causal effect estimation, including propensity-based, regression-based, and multiple robust estimators. We conduct a comprehensive theoretical analysis of their asymptotic properties under mild assumptions, with the ultimate goal of building a better understanding of the conditions under which some estimators can be expected to perform better. Extensive experiments across several semi-synthetic and real-world datasets validate the theoretical results and demonstrate the effectiveness of the proposed estimators.

Problem

• Estimate heterogeneous long-term causal effects
• Combine observational and experimental data
• Propose nonparametric estimators for robustness

Innovation

• Nonparametric estimators for causal effects
• Data combination for heterogeneous analysis
• Two-stage estimation methodology