Doubly robust uniform confidence band for the conditional average treatment effect function

By S. Lee, Ryo Okui, Yoon-Jae Whang. 2016

94 citations recorded by the source corpus.

In this paper, we propose a doubly robust method to estimate the heterogeneity of the average treatment effect with respect to observed covariates of interest. We consider a situation where a large number of covariates are needed for identifying the average treatment effect but the covariates of interest for analyzing heterogeneity are of much lower dimension. Our proposed estimator is doubly robust and avoids the curse of dimensionality. We propose a uniform confidence band that is easy to compute, and we illustrate its usefulness via Monte Carlo experiments and an application to the effects of smoking on birth weights.

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

Double/De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers (2018, background): “Prominent examples of the debiased CATE literature include Wang et al. (2010), van der Laan and Luedtke (2014), Luedtke and Van Der Laan (2016), Nie and Wager (2017), Lee et al. (2017), and most recently Kennedy (2020).”
Nonparametric Tests for Treatment Effect Heterogeneity With Duration Outcomes (2016, background): “This is particularly attractive when the dimension of X is moderate so one can plausibly rely on the unconfoundedness assumption, but the covariates of interest for analyzing heterogeneity are of much lower dimension (see, e.g., Abrevaya, Hsu, and Lieli 2015; Lee, Okui, and Whang 2017).”
What’s trending in difference-in-differences? A synthesis of the recent econometrics literature (2022, unknown): “…research has shown that data-adaptive/machine-learning procedures can be used to more flexibly estimate treatment effect heterogeneity in the context of RCTs or cross-sectional observational studies with unconfoundedness (e.g., Lee et al., 2017; Wager and Athey, 2018; Chernozhukov et al., 2020).”
Estimation of Conditional Average Treatment Effects With High-Dimensional Data (2019, result): “However, the Gumbel approximation is accurate only up to the logarithmic rate, as pointed out by Lee et al. (2017). The bootstrap approximation proposed in this paper has the advantage that the approximation error has a geometric rate of decline and the quality of the approximation is better than th”
Nonparametric estimation of causal heterogeneity under high-dimensional confounding (2019, methodology): “Conditional average treatment effects were investigated by Abrevaya et al. (2015) and Lee et al. (2016) who find that mother’s age is associated with increasingly negative effects of smoking.”
Towards optimal doubly robust estimation of heterogeneous causal effects (2020, background): “Lee et al. [2017] studied a local-linear version of the DR-Learner, but assumed the first-stage nuisance error was negligible.”
Doubly robust difference-in-differences estimators (2018, unknown): “On top of considering our proposed DR DID procedure, and the two-way fixed effect model adopted by Malesky et al. (2014), we also present results based on the DID regression estimator (6), and Abadie’s DID IPW estimator based on (8).”