Efficient Inference of Average Treatment Effects in High Dimensions via Approximate Residual Balancing

By Susan Athey, Guido W. Imbens, Stefan Wager. 2016

50 citations recorded by the source corpus.

Subfields: Statistics and Probability, Causal Inference & Discovery

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

Citations in the corpus

Cross-fitting and fast remainder rates for semiparametric estimation (2017, methodology): “Estimators based on approximating the reciprocal of the propensity score have been considered by Robins et al. (2007), Athey, Imbens, and Wager (2017), and recently in independent work by Hirschberg and Wager (2017).”
Panning for Gold: Model-free Knockoffs for High-dimensional Controlled Variable Selection (2016, result): “literature uses matching and propensity scores for approximately valid inference, but extending these methods to high dimensions is still a topic of current research, requiring similar assumptions and asymptotic approximations to the aforementioned high-dimensional GLM literature (Athey et al., 2016”
NBER WORKING PAPER SERIES BALANCING , REGRESSION , DIFFERENCE-IN-DIFFERENCES AND SYNTHETIC CONTROL METHODS : A SYNTHESIS (2016, unknown): “[2012, 2016], Hainmueller [2012], Imai and Ratkovic [2014], Athey et al. [2016]. In general, however, they will be different.”
Estimating individual treatment effect: generalization bounds and algorithms (2016, methodology): “Others show how to adapt high-dimensional regression methods such as Lasso to consistently estimate treatment effect, again achieving semi-parametric rates [6, 2].”
Locally Robust Semiparametric Estimation (2016, background): “In interesting related work, Athey et al. (2016) show root-n consistent estimation of an average treatment effect is possible under very weak conditions on the propensity score, under strong sparsity of the regression function. Thus, for machine learning the conditions here and in Athey et al. (2016”
Panning for gold: ‘model‐X’ knockoffs for high dimensional controlled variable selection (2016, result): “…uses matching and propensity scores for approximately valid inference, but extending these methods to high dimensions is still a topic of current research, requiring similar assumptions and asymptotic approximations to the aforementioned high-dimensional GLM literature (Athey et al., 2016).”
High-dimensional regression adjustments in randomized experiments (2016, background): “In a setting where treatment propensity may depend on covariates, simply fitting low-risk regression models to the treatment and control samples via cross-validation is not advised, as there exist regression adjustments that have low predictive error but yield severely biased estimates of the averag”
Estimating Average Treatment Effects: Supplementary Analyses and Remaining Challenges (2017, methodology): “[2013]), the ARB estimator (Athey et al. [2016]), and the closely related TML and DML estimators (Van Der Laan and Rubin [2006], Chernozhukov et al.”
Distilling the Outcomes of Personal Experiences: A Propensity-scored Analysis of Social Media (2017, background): “This highdimensional analysis accounts for as many covariates as are available that could predict the likelihood of a user to have the experience, making the assumption of unconfoundedness more plausible [6].”