Towards Robust Causal Effect Identification Beyond Markov Equivalence

2025/06/18 by Teh, Kai Z., Sadeghi, Kayvan, Soo, Terry
#FOS: Computer and information sciences #Methodology (stat.ME)

paper · doi:10.48550/arxiv.2506.15561

Abstract

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.

Related

• Causal Identification under Markov Equivalence
• Towards Bounding Causal Effects under Markov Equivalence
• On the Representation of Causal Background Knowledge and its Applications in Causal Inference
• A Survey on Causal Discovery: Theory and Practice
• An introduction to causal discovery