Probabilistic latent variable models for distinguishing between cause and effect

Part of Advances in Neural Information Processing Systems 23 (NIPS 2010)

Bibtex Metadata Paper Supplemental


Oliver Stegle, Dominik Janzing, Kun Zhang, Joris M. Mooij, Bernhard Schölkopf


We propose a novel method for inferring whether X causes Y or vice versa from joint observations of X and Y. The basic idea is to model the observed data using probabilistic latent variable models, which incorporate the effects of unobserved noise. To this end, we consider the hypothetical effect variable to be a function of the hypothetical cause variable and an independent noise term (not necessarily additive). An important novel aspect of our work is that we do not restrict the model class, but instead put general non-parametric priors on this function and on the distribution of the cause. The causal direction can then be inferred by using standard Bayesian model selection. We evaluate our approach on synthetic data and real-world data and report encouraging results.