Learning high-dimensional directed acyclic graphs with latent and selection variables

2011/04/30 by Diego Colombo, Marloes H. Maathuis, Markus Kalisch +1 · 4 citations
Mathematics · Computer Science · #stat.ME #cs.LG #math.ST #stat.TH

paper · pdf · doi:10.1214/11-aos940

published as Annals of Statistics 2012, Vol. 40, No. 1, 294-321 · Published in at http://dx.doi.org/10.1214/11-AOS940 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

arxiv created 2012/05/29 · arxiv updated 2012/05/30

Abstract

We consider the problem of learning causal information between random variables in directed acyclic graphs (DAGs) when allowing arbitrarily many latent and selection variables. The FCI (Fast Causal Inference) algorithm has been explicitly designed to infer conditional independence and causal information in such settings. However, FCI is computationally infeasible for large graphs. We therefore propose the new RFCI algorithm, which is much faster than FCI. In some situations the output of RFCI is slightly less informative, in particular with respect to conditional independence information. However, we prove that any causal information in the output of RFCI is correct in the asymptotic limit. We also define a class of graphs on which the outputs of FCI and RFCI are identical. We prove consistency of FCI and RFCI in sparse high-dimensional settings, and demonstrate in simulations that the estimation performances of the algorithms are very similar. All software is implemented in the R-package pcalg.

Cited by

• From Local to Cluster: A Unified Framework for Causal Discovery with Latent Variables
• GENESIS: Towards Explainable Causal Discovery
• Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports
• Semiparametric Causal Discovery and Inference with Invalid Instruments

Related

• Learning Directed Acyclic Graphs from Partial Orderings
• Robust causal structure learning with some hidden variables
• Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias
• Towards Scalable Bayesian Learning of Causal DAGs
• Learning Sparse Causal Models is not NP-hard