Open Access
February 2012 Learning high-dimensional directed acyclic graphs with latent and selection variables
Diego Colombo, Marloes H. Maathuis, Markus Kalisch, Thomas S. Richardson
Ann. Statist. 40(1): 294-321 (February 2012). DOI: 10.1214/11-AOS940


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.


Download Citation

Diego Colombo. Marloes H. Maathuis. Markus Kalisch. Thomas S. Richardson. "Learning high-dimensional directed acyclic graphs with latent and selection variables." Ann. Statist. 40 (1) 294 - 321, February 2012.


Published: February 2012
First available in Project Euclid: 4 April 2012

zbMATH: 1246.62131
MathSciNet: MR3014308
Digital Object Identifier: 10.1214/11-AOS940

Primary: 62-04 , 62H12 , 62M45
Secondary: 68T30

Keywords: Causal structure learning , consistency , FCI algorithm , high-dimensionality , maximal ancestral graphs (MAGs) , partial ancestral graphs (PAGs) , RFCI algorithm , Sparsity

Rights: Copyright © 2012 Institute of Mathematical Statistics

Vol.40 • No. 1 • February 2012
Back to Top