Testing whether linear equations are causal: A free probability theory approach
We propose a method that infers whether linear relations between two high-dimensional variables X and Y are due to a causal influence from X to Y or from Y to X. The earlier proposed so-called Trace Method is extended to the regime where the dimension of the observed variables exceeds the sample size. Based on previous work, we postulate conditions that characterize a causal relation between X and Y . Moreover, we describe a statistical test and argue that both causal directions are typically rejected if there is a common cause. A full theoretical analysis is presented for the deterministic case but our approach seems to be valid for the noisy case, too, for which we additionally present an approach based on a sparsity constraint. The discussed method yields promising results for both simulated and real world data.
Author(s): | Zscheischler, J. and Janzing, D. and Zhang, K. |
Pages: | 839-847 |
Year: | 2011 |
Month: | July |
Day: | 0 |
Editors: | Cozman, F.G. , A. Pfeffer |
Publisher: | AUAI Press |
Bibtex Type: | Conference Paper (inproceedings) |
Address: | Corvallis, OR, USA |
Event Name: | 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011) |
Event Place: | Barcelona, Spain |
Digital: | 0 |
Electronic Archiving: | grant_archive |
ISBN: | 978-0-9749039-7-2 |
Links: |
BibTex
@inproceedings{ZscheischlerJZ2011, title = {Testing whether linear equations are causal: A free probability theory approach}, abstract = {We propose a method that infers whether linear relations between two high-dimensional variables X and Y are due to a causal influence from X to Y or from Y to X. The earlier proposed so-called Trace Method is extended to the regime where the dimension of the observed variables exceeds the sample size. Based on previous work, we postulate conditions that characterize a causal relation between X and Y . Moreover, we describe a statistical test and argue that both causal directions are typically rejected if there is a common cause. A full theoretical analysis is presented for the deterministic case but our approach seems to be valid for the noisy case, too, for which we additionally present an approach based on a sparsity constraint. The discussed method yields promising results for both simulated and real world data.}, pages = {839-847}, editors = {Cozman, F.G. , A. Pfeffer}, publisher = {AUAI Press}, address = {Corvallis, OR, USA}, month = jul, year = {2011}, slug = {zscheischlerjz2011}, author = {Zscheischler, J. and Janzing, D. and Zhang, K.}, month_numeric = {7} }