Conditional Instrumental Variable Regression with Representation Learning for Causal Inference
This addresses the challenge of causal inference in fields like economics or healthcare where linearity assumptions and strict instrumental variable conditions are impractical, though it is an incremental improvement over existing IV methods.
The paper tackles the problem of estimating causal effects from observational data with unobserved confounders by proposing a non-linear conditional instrumental variable regression method, which shows competitive performance against state-of-the-art estimators and superiority in handling non-linear situations.
This paper studies the challenging problem of estimating causal effects from observational data, in the presence of unobserved confounders. The two-stage least square (TSLS) method and its variants with a standard instrumental variable (IV) are commonly used to eliminate confounding bias, including the bias caused by unobserved confounders, but they rely on the linearity assumption. Besides, the strict condition of unconfounded instruments posed on a standard IV is too strong to be practical. To address these challenging and practical problems of the standard IV method (linearity assumption and the strict condition), in this paper, we use a conditional IV (CIV) to relax the unconfounded instrument condition of standard IV and propose a non-linear CIV regression with Confounding Balancing Representation Learning, CBRL.CIV, for jointly eliminating the confounding bias from unobserved confounders and balancing the observed confounders, without the linearity assumption. We theoretically demonstrate the soundness of CBRL.CIV. Extensive experiments on synthetic and two real-world datasets show the competitive performance of CBRL.CIV against state-of-the-art IV-based estimators and superiority in dealing with the non-linear situation.