High-Dimensional Methods and Inference on Structural and Treatment Effects

By Alexandre Belloni, Victor Chernozhukov, Christian Hansen. 2013

707 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Statistics and Probability

In Causal Inference & Discovery

Citations in the corpus

Double/De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers (2018, background): “[1991]; Newey [1994a]; Bickel et al. [1993]; Robins and Rotnitzky [1995]; Van der Vaart [2000]], that do not apply to the current high-dimensional setting.”
Overlap in observational studies with high-dimensional covariates (2017, methodology): “If τ(X1:p) is assumed constant, for example, in the case of the partial linear model (Belloni et al., 2014; Farrell, 2015), then estimation of τATE only requires that strict overlap hold with positive probability, rather than with probability 1.”
A Minimax Surrogate Loss Approach to Conditional Difference Estimation (2018, background): “A large body of work in the causal inference community has focused on estimating average treatment effects (ATE) through linear models [30, 31, 32, 15, 26, 33, 4, 5], where the coefficient for the treatment variable provides an estimate for the ATE.”
Politician Family Networks and Electoral Outcomes: Evidence from the Philippines (2017, methodology): “Following Belloni et al. (2014), in Column 6, we select the optimal set of covariates using the double LASSO procedure.”
Estimation of Conditional Average Treatment Effects With High-Dimensional Data (2019, methodology): “The first approach is used by Belloni et al. (2017) in estimating unconditional treatment effects. In proposing and studying these estimators, we contribute to two recent strands of the econometrics literature. First, we advance the currently available flexible methods for the estimation of reduced ”
Does Diversity Matter for Health? Experimental Evidence from Oakland (2018, neutral): “[17] Belloni, Alexandre, Victor Chernozhukov, and Christian Hansen.”
Synthetic Difference In Differences (2018, neutral): “…assume any lower bounds for nonzero values of L ; in fact can accommodate arbitrarily many nonzero but very small singular values, much like, e.g., Belloni, Chernozhukov, and Hansen ( 2014 ) can accommodate arbitrarily many nonzero but very small signal coefficients in a high-dimensional…”
Poorly Measured Confounders are More Useful on the Left than on the Right (2017, background): “The literatures along the lines of Altonji, Elder, and Taber (2005) and Belloni, Chernozhukov, and Hansen (2014b) all start from the premise that there is a set of regressors xi so that regression (2) is preferable, at least in principle.”
Social Networks, Reputation, and Commitment: Evidence From a Savings Monitors Experiment (2019, methodology): “This is the new technique called double post-LASSO of Belloni et al. (2014a) (see also Belloni et al. (2014b)).”
Data Science of the People , for the People , by the People : A Viewpoint on an Emerging Dichotomy (2015, background): “In contrast, there continue to be new data science methods developed for Type A applications, most recently incorporating ideas from high-dimensional machine learning, because causality is so critical to many Type A applications that it has to be a part of the inference objective no matter what [8, ”
Beautiful city: Leisure amenities and urban growth (2019, background): “It is problematic to keep experimenting with alternate potential amenities ex post, lest we collectively overfit urban growth equations (Sala-i-Martin, 1997, Belloni, Chernozhukov, and Hansen, 2014).”