De-biased Machine Learning in Instrumental Variable Models for Treatment Effects
We introduce a de-biased machine learning (DML) approach to estimating complier parameters with high-dimensional data. Complier parameters include local average treatment effect, average complier characteristics, and complier counterfactual outcome distributions. In our approach, the de-biasing is i...
Main Authors: | , |
---|---|
Format: | Report |
Language: | unknown |
Subjects: | |
Online Access: | http://arxiv.org/pdf/1909.05244 |
id |
ftrepec:oai:RePEc:arx:papers:1909.05244 |
---|---|
record_format |
openpolar |
spelling |
ftrepec:oai:RePEc:arx:papers:1909.05244 2024-04-14T08:10:55+00:00 De-biased Machine Learning in Instrumental Variable Models for Treatment Effects Rahul Singh Liyang Sun http://arxiv.org/pdf/1909.05244 unknown http://arxiv.org/pdf/1909.05244 preprint ftrepec 2024-03-19T10:38:04Z We introduce a de-biased machine learning (DML) approach to estimating complier parameters with high-dimensional data. Complier parameters include local average treatment effect, average complier characteristics, and complier counterfactual outcome distributions. In our approach, the de-biasing is itself performed by machine learning, a variant called automatic de-biased machine learning (Auto-DML). By regularizing the balancing weights, it does not require ad hoc trimming or censoring. We prove our estimator is consistent, asymptotically normal, and semi-parametrically efficient. We use the new approach to estimate the effect of 401(k) participation on the distribution of net financial assets. Report DML RePEc (Research Papers in Economics) |
institution |
Open Polar |
collection |
RePEc (Research Papers in Economics) |
op_collection_id |
ftrepec |
language |
unknown |
description |
We introduce a de-biased machine learning (DML) approach to estimating complier parameters with high-dimensional data. Complier parameters include local average treatment effect, average complier characteristics, and complier counterfactual outcome distributions. In our approach, the de-biasing is itself performed by machine learning, a variant called automatic de-biased machine learning (Auto-DML). By regularizing the balancing weights, it does not require ad hoc trimming or censoring. We prove our estimator is consistent, asymptotically normal, and semi-parametrically efficient. We use the new approach to estimate the effect of 401(k) participation on the distribution of net financial assets. |
format |
Report |
author |
Rahul Singh Liyang Sun |
spellingShingle |
Rahul Singh Liyang Sun De-biased Machine Learning in Instrumental Variable Models for Treatment Effects |
author_facet |
Rahul Singh Liyang Sun |
author_sort |
Rahul Singh |
title |
De-biased Machine Learning in Instrumental Variable Models for Treatment Effects |
title_short |
De-biased Machine Learning in Instrumental Variable Models for Treatment Effects |
title_full |
De-biased Machine Learning in Instrumental Variable Models for Treatment Effects |
title_fullStr |
De-biased Machine Learning in Instrumental Variable Models for Treatment Effects |
title_full_unstemmed |
De-biased Machine Learning in Instrumental Variable Models for Treatment Effects |
title_sort |
de-biased machine learning in instrumental variable models for treatment effects |
url |
http://arxiv.org/pdf/1909.05244 |
genre |
DML |
genre_facet |
DML |
op_relation |
http://arxiv.org/pdf/1909.05244 |
_version_ |
1796308573750296576 |