Estimating Individualized Causal Effect with Confounded Instruments

Wang, Haotian; Yang, Wenjing; Yang, Longqi; Wu, Anpeng; Xu, Liyang; Ren, Jian; Wu, Fei; Kuang, Kun

doi:10.1145/3534678.3539335

Cited by 5 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The IV approach strongly relies on a predefined IV, which is required to be independent of all latent confounders and have a causal effect on the outcome only through its direct effect on the treatment. Some IV-based methods have been developed to address latent confounding in causal effect estimation using observational data in the static setting (Bowden and Turkington 1990;Hartford, Lewis et al 2017;Wang, Yang et al 2022). However, only a few IV-based methods are available for the longitudinal setting (Martinussen, Vansteelandt et al 2017).…”

Section: Introductionmentioning

confidence: 99%

Instrumental Variable Estimation for Causal Inference in Longitudinal Data with Time-Dependent Latent Confounders

Cheng,

Xu,

et al. 2024

AAAI

View full text Add to dashboard Cite

Causal inference from longitudinal observational data is a challenging problem due to the difficulty in correctly identifying the time-dependent confounders, especially in the presence of latent time-dependent confounders. Instrumental variable (IV) is a powerful tool for addressing the latent confounders issue, but the traditional IV technique cannot deal with latent time-dependent confounders in longitudinal studies. In this work, we propose a novel Time-dependent Instrumental Factor Model (TIFM) for time-varying causal effect estimation from data with latent time-dependent confounders. At each time-step, the proposed TIFM method employs the Recurrent Neural Network (RNN) architecture to infer latent IV, and then uses the inferred latent IV factor for addressing the confounding bias caused by the latent time-dependent confounders. We provide a theoretical analysis for the proposed TIFM method regarding causal effect estimation in longitudinal data. Extensive evaluation with synthetic datasets demonstrates the effectiveness of TIFM in addressing causal effect estimation over time. We further apply TIFM to a climate dataset to showcase the potential of the proposed method in tackling real-world problems.

show abstract

Section: Introductionmentioning

confidence: 99%