Latent Variable Causal Discovery under Selection Bias
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911315627343872 |
|---|---|
| author | Dai, Haoyue Qiu, Yiwen Ng, Ignavier Dong, Xinshuai Spirtes, Peter Zhang, Kun |
| author_facet | Dai, Haoyue Qiu, Yiwen Ng, Ignavier Dong, Xinshuai Spirtes, Peter Zhang, Kun |
| contents | Addressing selection bias in latent variable causal discovery is important yet underexplored, largely due to a lack of suitable statistical tools: While various tools beyond basic conditional independencies have been developed to handle latent variables, none have been adapted for selection bias. We make an attempt by studying rank constraints, which, as a generalization to conditional independence constraints, exploits the ranks of covariance submatrices in linear Gaussian models. We show that although selection can significantly complicate the joint distribution, interestingly, the ranks in the biased covariance matrices still preserve meaningful information about both causal structures and selection mechanisms. We provide a graph-theoretic characterization of such rank constraints. Using this tool, we demonstrate that the one-factor model, a classical latent variable model, can be identified under selection bias. Simulations and real-world experiments confirm the effectiveness of using our rank constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latent Variable Causal Discovery under Selection Bias Dai, Haoyue Qiu, Yiwen Ng, Ignavier Dong, Xinshuai Spirtes, Peter Zhang, Kun Machine Learning Addressing selection bias in latent variable causal discovery is important yet underexplored, largely due to a lack of suitable statistical tools: While various tools beyond basic conditional independencies have been developed to handle latent variables, none have been adapted for selection bias. We make an attempt by studying rank constraints, which, as a generalization to conditional independence constraints, exploits the ranks of covariance submatrices in linear Gaussian models. We show that although selection can significantly complicate the joint distribution, interestingly, the ranks in the biased covariance matrices still preserve meaningful information about both causal structures and selection mechanisms. We provide a graph-theoretic characterization of such rank constraints. Using this tool, we demonstrate that the one-factor model, a classical latent variable model, can be identified under selection bias. Simulations and real-world experiments confirm the effectiveness of using our rank constraints. |
| title | Latent Variable Causal Discovery under Selection Bias |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.11219 |