Towards Robust Causal Effect Identification Beyond Markov Equivalence
By: Kai Z. Teh, Kayvan Sadeghi, Terry Soo
Potential Business Impact:
Finds causes even when rules are unclear.
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.
Similar Papers
Causal Identification in Time Series Models
Machine Learning (CS)
Finds hidden causes in changing data.
Entropic Causal Inference: Graph Identifiability
Machine Learning (CS)
Finds cause and effect from data.
Complete Characterization for Adjustment in Summary Causal Graphs of Time Series
Statistics Theory
Finds hidden causes in past events.