EconBase
← All papers

Inference on Treatment Effects After Selection Amongst High-Dimensional Controls

Alexandre Belloni, Victor Chernozhukov, Christian Hansen

arXiv 31 Dec 2011 · Statistics — Methodology · 31 citations (OpenAlex)

arXiv:1201.0224 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We propose robust methods for inference on the effect of a treatment variable on a scalar outcome in the presence of very many controls. Our setting is a partially linear model with possibly non-Gaussian and heteroscedastic disturbances. Our analysis allows the number of controls to be much larger than the sample size. To make informative inference feasible, we require the model to be approximately sparse; that is, we require that the effect of confounding factors can be controlled for up to a small approximation error by conditioning on a relatively small number of controls whose identities are unknown. The latter condition makes it possible to estimate the treatment effect by selecting approximately the right set of controls. We develop a novel estimation and uniformly valid inference method for the treatment effect in this setting, called the "post-double-selection" method. Our results apply to Lasso-type methods used for covariate selection as well as to any other model selection method that is able to find a sparse model with good approximation properties. The main attractive feature of our method is that it allows for imperfect selection of the controls and provides confidence intervals that are valid uniformly across a large class of models. In contrast, standard post-model selection estimators fail to provide uniform inference even in simple cases with a small, fixed number of controls. Thus our method resolves the problem of uniform inference after model selection for a large, interesting class of models. We illustrate the use of the developed methods with numerical simulations and an application to the effect of abortion on crime rates.

Citation extraction

56
references
123
in-text mentions
56
distinct cited
4
self-citations
17,084
main-text words

appendix boundary found by appendix_command · 56% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Donohue III and Levitt (2001) The Impact of Legalized Abortion on Crime1.000203100%
2Belloni, Chen, Chernozhukov, and Hansen (2010) Sparse Models and Methods for Optimal Instruments with an Application to Eminent Domain0.9507486%
3Bickel, Ritov, and Tsybakov (2009) Simultaneous analysis of Lasso and Dantzig selector0.92843100%
4Belloni and Chernozhukov (2011) Least Squares After Model Selection in High-dimensional Sparse Models0.9098675%
5Cattaneo, Jansson, and Newey (2010) Alternative Asymptotics and the Partially Linear Model with Many Regressors0.87452100%
6Foote and Goetz (2008) The Impact of Legalized Abortion on Crime: Comment0.81142100%
7Rudelson and Zhou (2011) Reconstruction from anisotropic random measurements0.7375340%
8Belloni, Chernozhukov, and Hansen (2011) Inference for High-Dimensional Sparse Econometric Models self0.73732100%
9Candes and Tao (2007) The Dantzig selector: statistical estimation when p is much larger than n0.64422100%
10Frank and Friedman (1993) A Statistical View of Some Chemometrics Regression Tools0.64422100%

Showing the top 10 of 56 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Program Evaluation and Causal Inference with High-Dimensional Data1.000125
2Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations1.00064
3Inference in High Dimensional Panel Models with an Application to Gun Control0.916136
4Machine Learning Advances for Time Series Forecasting0.87462
5Deep Learning for Individual Heterogeneity0.84343
6Double/Debiased Machine Learning for Treatment and Structural Parameters0.84333
7Estimation and Inference of Treatment Effects with L2-Boosting in High-Dimensional Settings0.75474
8Valid Simultaneous Inference in High-Dimensional Settings (with the HDM Package for R)0.73732
9Deep Neural Networks for Estimation and Inference0.73732
10Heterogeneous Endogenous Effects in Networks0.64422