Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.15254 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912838523551744 |
|---|---|
| author | Schur, Felix Pfister, Niklas Ding, Peng Mukherjee, Sach Peters, Jonas |
| author_facet | Schur, Felix Pfister, Niklas Ding, Peng Mukherjee, Sach Peters, Jonas |
| contents | We study the problem of estimating causal effects under hidden confounding in the following unpaired data setting: we observe some covariates $X$ and an outcome $Y$ under different experimental conditions (environments) but do not observe them jointly; we either observe $X$ or $Y$. Under appropriate regularity conditions, the problem can be cast as an instrumental variable (IV) regression with the environment acting as a (possibly high-dimensional) instrument. When there are many environments but only a few observations per environment, standard two-sample IV estimators fail to be consistent. We propose a GMM-type estimator based on cross-fold sample splitting of the instrument-covariate sample and prove that it is consistent as the number of environments grows but the sample size per environment remains constant. We further extend the method to sparse causal effects via $\ell_1$-regularized estimation and post-selection refitting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15254 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Many Experiments, Few Repetitions, Unpaired Data, and Sparse Effects: Is Causal Inference Possible? Schur, Felix Pfister, Niklas Ding, Peng Mukherjee, Sach Peters, Jonas Machine Learning Artificial Intelligence We study the problem of estimating causal effects under hidden confounding in the following unpaired data setting: we observe some covariates $X$ and an outcome $Y$ under different experimental conditions (environments) but do not observe them jointly; we either observe $X$ or $Y$. Under appropriate regularity conditions, the problem can be cast as an instrumental variable (IV) regression with the environment acting as a (possibly high-dimensional) instrument. When there are many environments but only a few observations per environment, standard two-sample IV estimators fail to be consistent. We propose a GMM-type estimator based on cross-fold sample splitting of the instrument-covariate sample and prove that it is consistent as the number of environments grows but the sample size per environment remains constant. We further extend the method to sparse causal effects via $\ell_1$-regularized estimation and post-selection refitting. |
| title | Many Experiments, Few Repetitions, Unpaired Data, and Sparse Effects: Is Causal Inference Possible? |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.15254 |