ParKCa: Causal Inference with Partially Known Causes
Machine Learning
2020-11-13 v4 Applications
Machine Learning
Abstract
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.
Cite
@article{arxiv.2003.07952,
title = {ParKCa: Causal Inference with Partially Known Causes},
author = {Raquel Aoki and Martin Ester},
journal= {arXiv preprint arXiv:2003.07952},
year = {2020}
}
Comments
12 pages, 4 figures, Pacific Symposium on Biocomputing - 2021 World Scientific Publishing Co., Singapore, http://psb.stanford.edu/