Estimating Individual Treatment Effect in Observational Data Using Random Forest Methods

By Min Lu, Saad Sadiq, Daniel Feaster, Hemant Ishwaran. 2017

160 citations recorded by the source corpus.

ABSTRACT Estimation of individual treatment effect in observational data is complicated due to the challenges of confounding and selection bias. A useful inferential framework to address this is the counterfactual (potential outcomes) model, which takes the hypothetical stance of asking what if an individual had received both treatments. Making use of random forests (RF) within the counterfactual framework we estimate individual treatment effects by directly modeling the response. We find that accurate estimation of individual treatment effects is possible even in complex heterogenous settings but that the type of RF approach plays an important role in accuracy. Methods designed to be adaptive to confounding, when used in parallel with out-of-sample estimation, do best. One method found to be especially promising is counterfactual synthetic forests. We illustrate this new methodology by applying it to a large comparative effectiveness trial, Project Aware, to explore the role drug use plays in sexual risk. The analysis reveals important connections between risky behavior, drug usage, and sexual risk. Supplementary material for this article is available online.

Subfields: Statistics and Probability

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

Citations in the corpus

Deep Counterfactual Networks with Propensity-Dropout (2017, methodology): “Another less popular modeling approach is the “virtual twin” approach, which simply ﬁts a separate regression model for each of the treated and control populations (Lu et al., 2017).”
Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes (2017, methodology): “We provide a feature space interpretation of our method showing its relation to previous works on domain adaptation [6, 8], empirical risk minimization [13], and tree-based learning [4, 5, 7, 9].”
Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design (2018, unknown): “A similar study, but focusing only on random forest models, was conducted in ( Lu et al., 2017).”
GENERATIVE ADVERSARIAL NETS (2018, methodology): “More recent works focus on individualized treatment effects (Chipman et al. (2010); Wager & Athey (2017); Athey & Imbens (2016); Lu et al. (2017); Alaa & van der Schaar (2017); Porter et al. (2011); Johansson et al. (2016); Alaa et al. (2017); Louizos et al. (2017); Shalit et al. (2017)).”
Bayesian regression tree models for causal inference: regularization, confounding, and heterogeneous effects (2017, unknown): “(2012) and Lu et al. (2017). Finally, Wager and Athey”