Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ...
Double machine learning (DML) has become an increasingly popular tool for automated variable selection in high-dimensional settings. Even though the ability to deal with a large number of potential covariates can render selection-on-observables assumptions more plausible, there is at the same time a...
Main Authors: | , , |
---|---|
Format: | Text |
Language: | unknown |
Published: |
arXiv
2021
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2108.11294 https://arxiv.org/abs/2108.11294 |
id |
ftdatacite:10.48550/arxiv.2108.11294 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2108.11294 2023-06-11T04:11:17+02:00 Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ... Hünermund, Paul Louw, Beyers Caspi, Itamar 2021 https://dx.doi.org/10.48550/arxiv.2108.11294 https://arxiv.org/abs/2108.11294 unknown arXiv https://dx.doi.org/10.1515/jci-2022-0078 arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Econometrics econ.EM FOS Economics and business article-journal ScholarlyArticle Text Article 2021 ftdatacite https://doi.org/10.48550/arxiv.2108.1129410.1515/jci-2022-0078 2023-06-01T12:07:17Z Double machine learning (DML) has become an increasingly popular tool for automated variable selection in high-dimensional settings. Even though the ability to deal with a large number of potential covariates can render selection-on-observables assumptions more plausible, there is at the same time a growing risk that endogenous variables are included, which would lead to the violation of conditional independence. This paper demonstrates that DML is very sensitive to the inclusion of only a few "bad controls" in the covariate space. The resulting bias varies with the nature of the theoretical causal model, which raises concerns about the feasibility of selecting control variables in a data-driven way. ... : v4: published version ... Text DML DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Econometrics econ.EM FOS Economics and business |
spellingShingle |
Econometrics econ.EM FOS Economics and business Hünermund, Paul Louw, Beyers Caspi, Itamar Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ... |
topic_facet |
Econometrics econ.EM FOS Economics and business |
description |
Double machine learning (DML) has become an increasingly popular tool for automated variable selection in high-dimensional settings. Even though the ability to deal with a large number of potential covariates can render selection-on-observables assumptions more plausible, there is at the same time a growing risk that endogenous variables are included, which would lead to the violation of conditional independence. This paper demonstrates that DML is very sensitive to the inclusion of only a few "bad controls" in the covariate space. The resulting bias varies with the nature of the theoretical causal model, which raises concerns about the feasibility of selecting control variables in a data-driven way. ... : v4: published version ... |
format |
Text |
author |
Hünermund, Paul Louw, Beyers Caspi, Itamar |
author_facet |
Hünermund, Paul Louw, Beyers Caspi, Itamar |
author_sort |
Hünermund, Paul |
title |
Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ... |
title_short |
Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ... |
title_full |
Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ... |
title_fullStr |
Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ... |
title_full_unstemmed |
Double Machine Learning and Automated Confounder Selection -- A Cautionary Tale ... |
title_sort |
double machine learning and automated confounder selection -- a cautionary tale ... |
publisher |
arXiv |
publishDate |
2021 |
url |
https://dx.doi.org/10.48550/arxiv.2108.11294 https://arxiv.org/abs/2108.11294 |
genre |
DML |
genre_facet |
DML |
op_relation |
https://dx.doi.org/10.1515/jci-2022-0078 |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2108.1129410.1515/jci-2022-0078 |
_version_ |
1768386233480773632 |