Abstract
Several paradigms exist for modeling causal graphical models for discrete variables that can handle latent variables without explicitly modeling them quantitatively. Applying them to a problem domain consists of different steps: structure learning, parameter learning and using them for probabilistic or causal inference. We discuss two well-known formalisms, namely semi-Markovian causal models and maximal ancestral graphs and indicate their strengths and limitations. Previously an algorithm has been constructed that by combining elements from both techniques allows to learn a semi-Markovian causal models from a mixture of observational and experimental data. The goal of this paper is to recapitulate the integral learning process from observational and experimental data and to demonstrate how different types of inference can be performed efficiently in the learned models. We will do this by proposing an alternative representation for semi-Markovian causal models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Pearl, J.: Causality: Models, Reasoning and Inference. MIT Press, Cambridge (2000)
Tian, J., Pearl, J.: On the identification of causal effects. Technical Report (R-290- L), UCLA C.S. Lab (2002)
Richardson, T., Spirtes, P.: Ancestral graph markov models. Technical Report 375, Dept. of Statistics, University of Washington (2002)
Eberhardt, F., Glymour, C., Scheines, R.: On the number of experiments sufficient and in the worst case necessary to identify all causal relations among n variables. In: Proc. of the 21st Conference on Uncertainty in Artificial Intelligence (UAI), pp. 178–183 (2005)
Meganck, S., Leray, P., Manderick, B.: Learning causal bayesian networks from observations and experiments: A decision theoretic approach. In: Modeling Decisions in Artificial Intelligence. LNCS, pp. 58–69. Springer, Heidelberg (2006)
Spirtes, P., Glymour, C., Scheines, R.: Causation, Prediction and Search. MIT Press, Cambridge (2000)
Zhang, J.: Causal Inference and Reasoning in Causally Insufficient Systems. PhD thesis, Carnegie Mellon University (2006)
Meganck, S., Maes, S., Leray, P., Manderick, B.: Learning semi-markovian causal models using experiments. In: Proceedings of The third European Workshop on Probabilistic Graphical Models, PGM 2006 (2006)
Zhang, J., Spirtes, P.: A transformational characterization of markov equivalence for directed acyclic graphs with latent variables. In: Proc. of the 21st Conference on Uncertainty in Artificial Intelligence (UAI), pp. 667–674 (2005)
Tian, J.: Generating markov equivalent maximal ancestral graphs by single edge replacement. In: Proc. of the 21st Conference on Uncertainty in Artificial Intelligence (UAI), pp. 591–598 (2005)
Ali, A.R., Richardson, T., Spirtes, P., Zhang, J.: Orientation rules for constructing markov equivalence classes of maximal ancestral graphs. Technical Report 476, Dept. of Statistics, University of Washington (2005)
Spirtes, P., Meek, C., Richardson, T.: An algorithm for causal inference in the presence of latent variables and selection bias. In: Computation, Causation, and Discovery, pp. 211–252. AAAI Press, Menlo Park (1999)
Zhang, J., Spirtes, P.: A characterization of markov equivalence classes for ancestral graphical models. Technical Report 168, Dept. of Philosophy, Carnegie-Mellon University (2005)
Maes, S., Meganck, S., Leray, P.: An integral approach to causal inference with latent variables. In: Causality and Probability in the Sciences (Texts in Philosophy) (College Publications) (2007)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Francisco (1988)
Lauritzen, S.L., Spiegelhalter, D.J.: Local computations with probabilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society, series B 50, 157–244 (1988)
Richardson, T., Spirtes, P.: Causal inference via ancestral graph models. In: Oxford Statistical Science Series: Highly Structured Stochastic Systems. Oxford University Press, Oxford (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Meganck, S., Leray, P., Manderick, B. (2007). Causal Graphical Models with Latent Variables: Learning and Inference. In: Mellouli, K. (eds) Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2007. Lecture Notes in Computer Science(), vol 4724. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75256-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-75256-1_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75255-4
Online ISBN: 978-3-540-75256-1
eBook Packages: Computer ScienceComputer Science (R0)