Automatic Double Machine Learning for Continuous Treatment Effects

In this paper, we introduce and prove asymptotic normality for a new nonparametric estimator of continuous treatment effects. Specifically, we estimate the average dose-response function - the expected value of an outcome of interest at a particular level of the treatment level. We utilize tools fro...

Full description

Bibliographic Details
Main Author: Klosin, Sylvia
Format: Article in Journal/Newspaper
Language:unknown
Published: arXiv 2021
Subjects:
Econometrics econ.EM
Statistics Theory math.ST
Machine Learning stat.ML
FOS Economics and business
FOS Mathematics
FOS Computer and information sciences
DML
Online Access:https://dx.doi.org/10.48550/arxiv.2104.10334
https://arxiv.org/abs/2104.10334
id ftdatacite:10.48550/arxiv.2104.10334
record_format openpolar
spelling ftdatacite:10.48550/arxiv.2104.10334 2023-05-15T16:01:46+02:00 Automatic Double Machine Learning for Continuous Treatment Effects Klosin, Sylvia 2021 https://dx.doi.org/10.48550/arxiv.2104.10334 https://arxiv.org/abs/2104.10334 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Econometrics econ.EM Statistics Theory math.ST Machine Learning stat.ML FOS Economics and business FOS Mathematics FOS Computer and information sciences Article CreativeWork article Preprint 2021 ftdatacite https://doi.org/10.48550/arxiv.2104.10334 2022-03-10T14:24:23Z In this paper, we introduce and prove asymptotic normality for a new nonparametric estimator of continuous treatment effects. Specifically, we estimate the average dose-response function - the expected value of an outcome of interest at a particular level of the treatment level. We utilize tools from both the double debiased machine learning (DML) and the automatic double machine learning (ADML) literatures to construct our estimator. Our estimator utilizes a novel debiasing method that leads to nice theoretical stability and balancing properties. In simulations our estimator performs well compared to current methods. : 30 pages Article in Journal/Newspaper 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
Statistics Theory math.ST
Machine Learning stat.ML
FOS Economics and business
FOS Mathematics
FOS Computer and information sciences
spellingShingle Econometrics econ.EM
Statistics Theory math.ST
Machine Learning stat.ML
FOS Economics and business
FOS Mathematics
FOS Computer and information sciences
Klosin, Sylvia
Automatic Double Machine Learning for Continuous Treatment Effects
topic_facet Econometrics econ.EM
Statistics Theory math.ST
Machine Learning stat.ML
FOS Economics and business
FOS Mathematics
FOS Computer and information sciences
description In this paper, we introduce and prove asymptotic normality for a new nonparametric estimator of continuous treatment effects. Specifically, we estimate the average dose-response function - the expected value of an outcome of interest at a particular level of the treatment level. We utilize tools from both the double debiased machine learning (DML) and the automatic double machine learning (ADML) literatures to construct our estimator. Our estimator utilizes a novel debiasing method that leads to nice theoretical stability and balancing properties. In simulations our estimator performs well compared to current methods. : 30 pages
format Article in Journal/Newspaper
author Klosin, Sylvia
author_facet Klosin, Sylvia
author_sort Klosin, Sylvia
title Automatic Double Machine Learning for Continuous Treatment Effects
title_short Automatic Double Machine Learning for Continuous Treatment Effects
title_full Automatic Double Machine Learning for Continuous Treatment Effects
title_fullStr Automatic Double Machine Learning for Continuous Treatment Effects
title_full_unstemmed Automatic Double Machine Learning for Continuous Treatment Effects
title_sort automatic double machine learning for continuous treatment effects
publisher arXiv
publishDate 2021
url https://dx.doi.org/10.48550/arxiv.2104.10334
https://arxiv.org/abs/2104.10334
genre DML
genre_facet DML
op_rights arXiv.org perpetual, non-exclusive license
http://arxiv.org/licenses/nonexclusive-distrib/1.0/
op_doi https://doi.org/10.48550/arxiv.2104.10334
_version_ 1766397500038578176

Similar Items