Abstract
Graphical models based on chain graphs, which admit both directed and undirected edges, were introduced by by Lauritzen, Wermuth and Frydenberg as a generalization of graphical models based on undirected graphs, and acyclic directed graphs. More recently Andersson, Madigan and Perlman have given an alternative Markov property for chain graphs. This raises two questions: How are the two types of chain graphs to be mterpreted? In which situations should chain graph models be used and with which Markov property?
The undirected edges in a chain graph are often said to represent ‘symmetric’ relations. Several different symmetric structures are considered, and it is shown that although each leads to a different set of conditional independences, none of those considered corresponds to either of the chain graph Markov properties.
The Markov properties of undirected graphs, and directed graphs, including latent variables and selection variables, are compared to those that have been proposed for chain graphs. It is shown that there are qualitative differences between these Markov properties. As a corollary, it is proved that there are chain graphs which do not correspond to any cyclic or acyclic dlirected graph, even with latent or selection variables.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
S. A. Andersson, D. Madigan, and M. D. Perlman. An alternative Markov property for chain graphs. In F. V. Jensen and E. Horvitz, editors, Uncertainty in Artificial Intelligence: Proceedings of the12th Conference, pages 40–48, San Francisco, 1996. Morgan Kaufmann.
S. A. Andersson, D. Madigan, and M. D. Perlman. A new pathwise separation criterion for chain graphs. In preparation, 1997.
J. Besag. On spatial-temporal models and Markov fields. In Transactions of the7th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, pages 47–55. Academia, Prague, 1974.
J. Besag. Spatial interaction and the statistical analysis of lattice systems (with discussion). J. Royal Statist. Soc. Ser. B, 36: 302–309, 1974.
G. F. Cooper and E. Herskovits. A Bayesian method for the induction of probabilistic networks from data. Machine Learning, 9: 309–347, 1992.
D. R. Cox. Causality and graphical models. In Proceedings, 49th Session, volume 1 of Bulletin of the International Statistical Institute, pages 363–372, 1993.
D. R. Cox and N. Wermuth. Multivariate Dependencies: Models, Analysis and Interpretation. Chapman and Hall, London, 1996.
J. N. Darroch, S. L. Lauritzen, and T. P. Speed. Markov fields and log-linear models for contingency tables. Ann. Statist., 8: 522–539, 1980.
A. Dempster. Covariance selection. Biometrics, 28: 157–175, 1972.
F. M. Fisher. A correspondence principle for simultaneous equation models. Econometrica, 38 (1): 73–92, 1970.
M. Frydenberg. The chain graph Markov property. Scandin. J. Statist., 17: 333–353, 1990.
D. Geiger. Graphoids: a qualitative framework for probabilistic inference. PhD thesis, UCLA, 1990.
J. M. Hammersley and P. Clifford. Markov fields on finite graphs and lattices. Unpublished manuscript, 1971.
D. Hausman. Causal priority. Nous, 18: 261–279, 1984.
D. Beckerman, D. Geiger, and D. M. Chickering. Learning Bayesian networks: the combination of knowledge and statistical data. In B. Lopez de Mantaras and D. Poole, editors, Uncertainty in Artificial Intelligence: Proceedings of the10th Conference, pages 293–301, San Francisco, 1994. Morgan Kaufniann.
J. T. A. Koster. Markov properties of non-recursive causal models. Ann. Statist., 24: 2148–2178, October 1996.
S. L. Lauritzen. Graphical Models. Number 81 in Oxford Statistical Science Series. Springer-Verlag, 1993.
S. L. Lauritzen, A. P. Dawid, B. Larsen, and H.-G. Leimer. Independence properties of directed Markov fields. Networks, 20: 491–505, 1990.
S. L. Lauritzen and D. J. Spiegelhalter. Local computation with probabilities in graphical structures and their application to expert systems (with discussion). J. Royal Statist. Soc. Ser. B, 50 (2): 157–224, 1988.
S. L. Lauritzen and N. Wermuth. Graphical models for association between variables, some of which are qualitative and some quantitative. Ann. Statist., 17: 31–57, 1989.
C. Meek. Strong completeness and faithfulness in Bayesian networks. In P. Besnard and S. Hanks, editors, Uncertainty in Artificial Intelligence: Proceedings of the11th Conference, pages 403–410, San Francisco, 1995. Morgan Kaufmann.
J. Pearl. Probabilistic Reasoning in Intelligent Systems. Morgan Kaufman, 1988.
J. Pearl. Causal diagrams for empirical research (with discussion). Biometrika, 82: 669–690, 1995.
J. Pearl and R. Dechter. Identifying independencies in causal graphs with feedback. In F. V. Jensen and E. Horvitz, editors, Uncertainty in Artificial Intelligence: Proceedings of the 12th Conference, pages 454–461, San Francisco, 1996. Morgan Kaufmann.
J. Pearl and T. Verma. A theory of inferred causation. In J. A. Allen, R. Fikes, and E. Sandewall, editors, Principles of Knowledge Representation and Reasoning: Proceedings of the Second International Conference, pages 441–452, San Mateo, CA, 1991. Morgan Kaufmann.
T. S. Richardson. A discovery algorithm for directed cyclic graphs. In F. V. Jensen and E. Horvitz, editors, Uncertainty in Artificial Intelligence: Proceedings of the12th Conference, pages 454–461, San Francisco, 1996. Morgan Kaufmann.
T. S. Richardson. Models of feedback: interpretation and discovery. PhD thesis, Carnegie-Mellon University, 1996.
T. S. Richardson. A polynomial-time algorithm for deciding Markov equivalence of directed cyclic graphical models. In F. V. Jensen and E. Horvitz, editors, Uncertainty in Artificial Intelligence: Proceedings of the12th Conference, pages 462–469, San Francisco, 1996. Morgan Kaufmann.
T. P. Speed. A note on nearest-neighbour Gibbs and Markov distributions over graphs. Sankhya Ser. A, 41: 184–197, 1979.
P. Spirtes. Directed cyclic graphical representations of feedback models. In P. Besnard and S. Hanks, editors, Uncertainty in Artificial Intelligence: Proceedings of the11th Conference, pages 491–498, San Francisco, 1995. Morgan Kaufmann.
P. Spirtes, C. Glymour, and R. Scheines. Causation, Prediction and Search. Lecture Notes in Statistics. Oxford University Press, 1996.
P. Spirtes, C. Meek, and T.S. Richardson. Causal inference in the presence of latent variables and selection bias. In P. Besnard and S Hanks, editors, Uncertainty in Artificial Intelligence: Proceedings of the11th Conference, pages 403–410, San Francisco, 1995. Morgan Kaufmann.
P. Spirtes and T. S. Richardson. A polynomial-time algorithm for determining dag equivalence in the presence of latent variables and selection bias. In D. Madigan and P. Smyth, editors, Preliminary papers of the Sixth International Workshop on Al and Statistics, January 4–7, Fort Lauderdale, Florida, pages 489–501, 1997.
P. Spirtes and T. Verma. Equivalence of causal models with latent variables. Technical Report CMU-PHIL-33, Department of Philosophy, Carnegie Mellon University, October 1992.
R. H. Strotz and H. O. A. Wold. Recursive versus non-recursive systems: an attempt at synthesis. Econometrica, 28:417–427, 1960. ( Also in Causal Models in the Social Sciences, H.M. Blalock Jr. ed., Chicago: Aldine Atherton, 1971 ).
M. Studený and R. Bouckaert. On chain graph models for description of conditional independence structures. Ann. Statist., 1996. Accepted for publication.
T. Verma and J. Pearl. Equivalence and synthesis of causal models. In M. Henrion, R. Shachter, L. Kanal, and J. Lemmer, editors, Uncertainty in Artificial Intelligence: Proceedings of the12th Conference, pages 220–227, San Francisco, 1996. Morgan Kaufmann.
S. Wright. Correlation and Causation. J. Agricultural Research, 20: 557–585, 1921.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Richardson, T.S. (1998). Chain Graphs and Symmetric Associations. In: Jordan, M.I. (eds) Learning in Graphical Models. NATO ASI Series, vol 89. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-5014-9_9
Download citation
DOI: https://doi.org/10.1007/978-94-011-5014-9_9
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-6104-9
Online ISBN: 978-94-011-5014-9
eBook Packages: Springer Book Archive