Towards Bounding Causal Effects under Markov Equivalence
This work addresses the challenge of causal inference in practical applications where exact causal diagrams cannot be confidently specified, offering a more data-driven approach.
The paper tackles the problem of bounding causal effects when the true causal diagram is unknown, using only observational data and a Partial Ancestral Graph representing a Markov equivalence class; it provides an analytical algorithm for deriving these bounds and demonstrates it with synthetic and real data examples.
Predicting the effect of unseen interventions is a fundamental research question across the data sciences. It is well established that in general such questions cannot be answered definitively from observational data. This realization has fuelled a growing literature introducing various identifying assumptions, for example in the form of a causal diagram among relevant variables. In practice, this paradigm is still too rigid for many practical applications as it is generally not possible to confidently delineate the true causal diagram. In this paper, we consider the derivation of bounds on causal effects given only observational data. We propose to take as input a less informative structure known as a Partial Ancestral Graph, which represents a Markov equivalence class of causal diagrams and is learnable from data. In this more ``data-driven'' setting, we provide a systematic algorithm to derive bounds on causal effects that exploit the invariant properties of the equivalence class, and that can be computed analytically. We demonstrate our method with synthetic and real data examples.