Graph Machine Learning based Doubly Robust Estimator for Network Causal Effects
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910026183999488 |
|---|---|
| author | Khatami, Seyedeh Baharan Parikh, Harsh Chen, Haowei Roy, Sudeepa Salimi, Babak |
| author_facet | Khatami, Seyedeh Baharan Parikh, Harsh Chen, Haowei Roy, Sudeepa Salimi, Babak |
| contents | We address the challenge of inferring causal effects in social network data. This results in challenges due to interference -- where a unit's outcome is affected by neighbors' treatments -- and network-induced confounding factors. While there is extensive literature focusing on estimating causal effects in social network setups, a majority of them make prior assumptions about the form of network-induced confounding mechanisms. Such strong assumptions are rarely likely to hold especially in high-dimensional networks. We propose a novel methodology that combines graph machine learning approaches with the double machine learning framework to enable accurate and efficient estimation of direct and peer effects using a single observational social network. We demonstrate the semiparametric efficiency of our proposed estimator under mild regularity conditions, allowing for consistent uncertainty quantification. We demonstrate that our method is accurate, robust, and scalable via an extensive simulation study. We use our method to investigate the impact of Self-Help Group participation on financial risk tolerance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11332 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Graph Machine Learning based Doubly Robust Estimator for Network Causal Effects Khatami, Seyedeh Baharan Parikh, Harsh Chen, Haowei Roy, Sudeepa Salimi, Babak Machine Learning Social and Information Networks Methodology We address the challenge of inferring causal effects in social network data. This results in challenges due to interference -- where a unit's outcome is affected by neighbors' treatments -- and network-induced confounding factors. While there is extensive literature focusing on estimating causal effects in social network setups, a majority of them make prior assumptions about the form of network-induced confounding mechanisms. Such strong assumptions are rarely likely to hold especially in high-dimensional networks. We propose a novel methodology that combines graph machine learning approaches with the double machine learning framework to enable accurate and efficient estimation of direct and peer effects using a single observational social network. We demonstrate the semiparametric efficiency of our proposed estimator under mild regularity conditions, allowing for consistent uncertainty quantification. We demonstrate that our method is accurate, robust, and scalable via an extensive simulation study. We use our method to investigate the impact of Self-Help Group participation on financial risk tolerance. |
| title | Graph Machine Learning based Doubly Robust Estimator for Network Causal Effects |
| topic | Machine Learning Social and Information Networks Methodology |
| url | https://arxiv.org/abs/2403.11332 |