Score: 0

Towards Robust Causal Effect Identification Beyond Markov Equivalence

Published: June 18, 2025 | arXiv ID: 2506.15561v1

By: Kai Z. Teh, Kayvan Sadeghi, Terry Soo

Potential Business Impact:

Finds causes even when rules are unclear.

Business Areas:
A/B Testing Data and Analytics

Causal effect identification typically requires a fully specified causal graph, which can be difficult to obtain in practice. We provide a sufficient criterion for identifying causal effects from a candidate set of Markov equivalence classes with added background knowledge, which represents cases where determining the causal graph up to a single Markov equivalence class is challenging. Such cases can happen, for example, when the untestable assumptions (e.g. faithfulness) that underlie causal discovery algorithms do not hold.

Country of Origin
🇬🇧 United Kingdom

Page Count
8 pages

Category
Statistics:
Methodology