TabCF: Distributional Control Function Estimation with Tabular Foundation Models

2026-05-07

AI Summary

This work addresses the limitations of existing instrumental variable and control function approaches, which are largely confined to estimating mean causal effects and often require cumbersome hyperparameter tuning, thereby hindering efficient distributional causal inference. The paper introduces, for the first time, a tabular foundation model into distributional causal inference by integrating control function regression with copula approximation. This yields a unified framework that is both identification-transparent and lightweight in tuning, enabling efficient estimation of treatment effects on various distributional features—such as means and quantiles. Extensive experiments on multiple medium-scale synthetic and real-world datasets demonstrate that the proposed method substantially outperforms representative state-of-the-art approaches in both accuracy and practicality, establishing a strong baseline for distributional causal effect estimation.

Abstract

Instrumental variable (IV) and control function (CF) methods are powerful tools for causal effect estimation in the presence of unmeasured confounding, yet most existing approaches target only mean effects and/or demand substantial fitting and tuning effort. In this paper, we introduce a simple method, TabCF, for control function regression using tabular foundation models, which enables accurate, fast, identification-transparent, and tuning-light causal estimation of distributional quantities, such as interventional means and quantiles; we also propose a copula-based approximation for multivariate outcomes. TabCF performs favorably against representative methods across a broad range of small- to medium-sized synthetic and real data scenarios. The central message is two-fold: for practitioners, it highlights that TabCF is an effective tool for distributional causal inference; for researchers, it suggests that the proposed approach could be considered a strong baseline for future method development. Code is available at https://github.com/GepingChen/TabCF.

Problem

• instrumental variable
• control function
• causal inference
• distributional effects
• unmeasured confounding

Innovation

• Tabular Foundation Models
• Control Function Regression
• Distributional Causal Inference
• Instrumental Variables
• Copula Approximation