Identification-robust inference for the LATE with high-dimensional covariates ...
This paper investigates the local average treatment effect (LATE) with high-dimensional covariates, irrespective of the strength of identification. We propose a novel test statistic for the high-dimensional LATE, demonstrating that our test has uniformly correct asymptotic size. By employing the dou...
| Main Author: | |
|---|---|
| Format: | Report |
| Language: | unknown |
| Published: |
arXiv
2023
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.48550/arxiv.2302.09756 https://arxiv.org/abs/2302.09756 |
| id |
ftdatacite:10.48550/arxiv.2302.09756 |
|---|---|
| record_format |
openpolar |
| spelling |
ftdatacite:10.48550/arxiv.2302.09756 2023-10-01T03:55:40+02:00 Identification-robust inference for the LATE with high-dimensional covariates ... Ma, Yukun 2023 https://dx.doi.org/10.48550/arxiv.2302.09756 https://arxiv.org/abs/2302.09756 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Econometrics econ.EM FOS Economics and business Preprint article Article CreativeWork 2023 ftdatacite https://doi.org/10.48550/arxiv.2302.09756 2023-09-04T13:25:47Z This paper investigates the local average treatment effect (LATE) with high-dimensional covariates, irrespective of the strength of identification. We propose a novel test statistic for the high-dimensional LATE, demonstrating that our test has uniformly correct asymptotic size. By employing the double/debiased machine learning (DML) method to estimate nuisance parameters, we develop easy-to-implement algorithms for inference and confidence interval calculation of the high-dimensional LATE. Simulations indicate that our test is robust against both weak identification and high-dimensional setting concerning size control and power performance, outperforming other conventional tests. Applying the proposed test to railroad and population data to study the effect of railroad access on urban population growth, we observe the shorter length of confidence intervals and smaller point estimates for the railroad access coefficients compared to the conventional tests. ... : 45pages, 2 figures ... Report 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 Ma, Yukun Identification-robust inference for the LATE with high-dimensional covariates ... |
| topic_facet |
Econometrics econ.EM FOS Economics and business |
| description |
This paper investigates the local average treatment effect (LATE) with high-dimensional covariates, irrespective of the strength of identification. We propose a novel test statistic for the high-dimensional LATE, demonstrating that our test has uniformly correct asymptotic size. By employing the double/debiased machine learning (DML) method to estimate nuisance parameters, we develop easy-to-implement algorithms for inference and confidence interval calculation of the high-dimensional LATE. Simulations indicate that our test is robust against both weak identification and high-dimensional setting concerning size control and power performance, outperforming other conventional tests. Applying the proposed test to railroad and population data to study the effect of railroad access on urban population growth, we observe the shorter length of confidence intervals and smaller point estimates for the railroad access coefficients compared to the conventional tests. ... : 45pages, 2 figures ... |
| format |
Report |
| author |
Ma, Yukun |
| author_facet |
Ma, Yukun |
| author_sort |
Ma, Yukun |
| title |
Identification-robust inference for the LATE with high-dimensional covariates ... |
| title_short |
Identification-robust inference for the LATE with high-dimensional covariates ... |
| title_full |
Identification-robust inference for the LATE with high-dimensional covariates ... |
| title_fullStr |
Identification-robust inference for the LATE with high-dimensional covariates ... |
| title_full_unstemmed |
Identification-robust inference for the LATE with high-dimensional covariates ... |
| title_sort |
identification-robust inference for the late with high-dimensional covariates ... |
| publisher |
arXiv |
| publishDate |
2023 |
| url |
https://dx.doi.org/10.48550/arxiv.2302.09756 https://arxiv.org/abs/2302.09756 |
| 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.2302.09756 |
| _version_ |
1778524283782299648 |