Jointly Interventional and Observational Data: Estimation of Interventional Markov Equivalence Classes of Directed Acyclic Graphs
- 30 May 2014
- journal article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 77 (1) , 291-318
Abstract
Summary: In many applications we have both observational and (randomized) interventional data. We propose a Gaussian likelihood framework for joint modelling of such different data types, based on global parameters consisting of a directed acyclic graph and corresponding edge weights and error variances. Thanks to the global nature of the parameters, maximum likelihood estimation is reasonable with only one or few data points per intervention. We prove consistency of the Bayesian information criterion for estimating the interventional Markov equivalence class of directed acyclic graphs which is smaller than the observational analogue owing to increased partial identifiability from interventional data. Such an improvement in identifiability has immediate implications for tighter bounds for inferring causal effects. Besides methodology and theoretical derivations, we present empirical results from real and simulated data.Keywords
All Related Versions
Funding Information
- Swiss National Science Foundation (20PA20E-134493/1)
This publication has 11 references indexed in Scilit:
- Stability SelectionJournal of the Royal Statistical Society Series B: Statistical Methodology, 2010
- Estimating high-dimensional intervention effects from observational dataThe Annals of Statistics, 2009
- Learning Causal Bayesian Network Structures From Experimental DataJournal of the American Statistical Association, 2008
- Sparse inverse covariance estimation with the graphical lassoBiostatistics, 2007
- The max-min hill-climbing Bayesian network structure learning algorithmMachine Learning, 2006
- Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell DataScience, 2005
- A characterization of Markov equivalence classes for acyclic digraphsThe Annals of Statistics, 1997
- Learning Bayesian Networks is NP-Complete1996
- Causal diagrams for empirical researchBiometrika, 1995
- On the Choice of a Model to Fit Data from an Exponential FamilyThe Annals of Statistics, 1988