Debiased Machine Learning of Aggregated Intersection Bounds and Other Causal Parameters
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915275847237632 |
|---|---|
| author | Semenova, Vira |
| author_facet | Semenova, Vira |
| contents | This paper proposes a novel framework of aggregated intersection of regression functions, where the target parameter is obtained by averaging the minimum (or maximum) of a collection of regression functions over the covariate space. Such quantities include the lower and upper bounds on distributional effects (Frechet-Hoeffding, Makarov) and the optimal welfare in the statistical treatment choice problem. The proposed estimator -- the envelope score estimator -- is shown to have an oracle property, where the oracle knows the identity of the minimizer for each covariate value. I apply this result to the bounds in the Roy model and the Horowitz-Manski-Lee bounds with a discrete outcome. The proposed approach performs well empirically on the data from the Oregon Health Insurance Experiment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_00982 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Debiased Machine Learning of Aggregated Intersection Bounds and Other Causal Parameters Semenova, Vira Econometrics This paper proposes a novel framework of aggregated intersection of regression functions, where the target parameter is obtained by averaging the minimum (or maximum) of a collection of regression functions over the covariate space. Such quantities include the lower and upper bounds on distributional effects (Frechet-Hoeffding, Makarov) and the optimal welfare in the statistical treatment choice problem. The proposed estimator -- the envelope score estimator -- is shown to have an oracle property, where the oracle knows the identity of the minimizer for each covariate value. I apply this result to the bounds in the Roy model and the Horowitz-Manski-Lee bounds with a discrete outcome. The proposed approach performs well empirically on the data from the Oregon Health Insurance Experiment. |
| title | Debiased Machine Learning of Aggregated Intersection Bounds and Other Causal Parameters |
| topic | Econometrics |
| url | https://arxiv.org/abs/2303.00982 |