On Causal Identification Under Markov Equivalence

Abstract

In this work, we investigate the problem of computing an experimental distribution from a combination of the observational distribution and a partial qualitative description of the causal structure of the domain under investigation. This description is given by a partial ancestral graph (PAG) that represents a Markov equivalence class of causal diagrams, i.e., diagrams that entail the same conditional independence model over observed variables, and is learnable from the observational data. Accordingly, we develop a complete algorithm to compute the causal effect of an arbitrary set of intervention variables on an arbitrary outcome set.

Cite

Text

Jaber et al. "On Causal Identification Under Markov Equivalence." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/859

Markdown

[Jaber et al. "On Causal Identification Under Markov Equivalence." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/jaber2019ijcai-causal/) doi:10.24963/IJCAI.2019/859

BibTeX

@inproceedings{jaber2019ijcai-causal,
  title     = {{On Causal Identification Under Markov Equivalence}},
  author    = {Jaber, Amin and Zhang, Jiji and Bareinboim, Elias},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {6181-6185},
  doi       = {10.24963/IJCAI.2019/859},
  url       = {https://mlanthology.org/ijcai/2019/jaber2019ijcai-causal/}
}