Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders

By Ioana Bica, Ahmed M. Alaa, Mihaela van der Schaar. 2019

138 citations recorded by the source corpus.

The estimation of treatment effects is a pervasive problem in medicine. Existing methods for estimating treatment effects from longitudinal observational data assume that there are no hidden confounders, an assumption that is not testable in practice and, if it does not hold, leads to biased estimates. In this paper, we develop the Time Series Deconfounder, a method that leverages the assignment of multiple treatments over time to enable the estimation of treatment effects in the presence of multi-cause hidden confounders. The Time Series Deconfounder uses a novel recurrent neural network architecture with multitask output to build a factor model over time and infer latent variables that render the assigned treatments conditionally independent; then, it performs causal inference using these latent variables that act as substitutes for the multi-cause unobserved confounders. We provide a theoretical analysis for obtaining unbiased causal effects of time-varying exposures using the Time Series Deconfounder. Using both simulated and real data we show the effectiveness of our method in deconfounding the estimation of treatment responses over time.

Subfields: Statistics and Probability, Causal Inference & Discovery, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

In Causal Inference & Discovery

In Time-Series & Forecasting

Citations in the corpus

Toward Causal Representation Learning (2021, background): “While it may be useful to automate certain decisions, an understanding of causality may be necessary to recommend treatment options that are personalized and reliable [3], [6], [31], [164], [201], [224], [242], [273].”
Towards Causal Representation Learning (2021, background): “While it may be useful to automate certain decisions, an understanding of causality may be necessary to recommend treatment options that are personalized and reliable [201, 242, 224, 273, 6, 3, 30, 165].”
A Survey on Causal Inference (2020, background): “[18] infers substitute confounders that render the assigned treatments conditionally independent.”
From Real‐World Patient Data to Individualized Treatment Effects Using Machine Learning: Current and Future Methods to Address Underlying Challenges (2020, methodology): “For instance, Bica et al.(49) propose taking advantage of the sequential assignment of multiple treatments in order to estimate the effect”
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks (2020, background): “Moreover, another important research direction is to extend this work to the temporal causal inference setting [26–29] and estimate counterfactual outcomes for sequences of continuous interventions.”