ParKCa: Causal Inference with Partially Known Causes
This work addresses the challenge of discovering new causal relationships in domains like genetics where randomized experiments are impractical, though it appears incremental as it builds on existing methods.
The authors tackled the problem of causal inference from observational data by proposing ParKCA, a method that combines multiple causal inference techniques to identify new causes when some are already known. The results demonstrated that ParKCA inferred more causes than existing methods in both real-world and simulated Genome-wide association studies.
Methods for causal inference from observational data are an alternative for scenarios where collecting counterfactual data or realizing a randomized experiment is not possible. Adopting a stacking approach, our proposed method ParKCA combines the results of several causal inference methods to learn new causes in applications with some known causes and many potential causes. We validate ParKCA in two Genome-wide association studies, one real-world and one simulated dataset. Our results show that ParKCA can infer more causes than existing methods.