Artikel
The hardness of conditional independence testing
Suche in Medline nach
Autoren
-
Jonas Peters
- University of Copenhagen, Copenhagen, Denmark
-
Rajen Shah
- University of Cambridge, Cambridge, United Kingdom
| Veröffentlicht: | 26. Februar 2021 |
|---|
Gliederung
Text
It is a common saying that testing for conditional independence, i.e., testing whether two random vectors X and Y are independent, given Z, is a hard statistical problem if Z is a continuous random variable (or vector). In this work, we prove that conditional independence is indeed a particularly difficult hypothesis to test for and is fundamentally harder than testing for unconditional independence, for example. Solving it requires carefully chosen assumptions on the data generating process. We also provide a conditional independence test, the generalised covariance measure (GCM), that is explicit about such assumptions.
The authors declare that they have no competing interests.
The authors declare that an ethics committee vote is not required.
References
- 1.
- Shah R, Peters J. “The Hardness of Conditional Independence Testing and the Generalised Covariance Measure”. Annals of Statistics. Forthcoming.
