Abstract
Lattice conditional independence (LCI) models for multivariate normal data recently have been introduced for the analysis of non-monotone missing data patterns and of nonnested dependent linear regression models (≡ seemingly unrelated regressions). It is shown here that the class of LCI models coincides with a subclass of the class of graphical Markov models determined by acyclic digraphs (ADGs), namely, the subclass of transitive ADG models. An explicit graph-theoretic characterization of those ADGs that are Markov equivalent to some transitive ADG is obtained. This characterization allows one to determine whether a specific ADG D is Markov equivalent to some transitive ADG, hence to some LCI model, in polynomial time, without an exhaustive search of the (possibly superexponentially large) equivalence class [D]. These results do not require the existence or positivity of joint densities.
Similar content being viewed by others
References
T.W. Andersson, Maximum likelihood estimates for a multivariate normal distribution when some observations are missing, J. Amer. Statist. Assoc. 52 (1957) 200–203.
S.A. Andersson, The lattice structure of orthogonal linear models and orthogonal variance component models, Scand. J. Statist. 17 (1990) 287–319.
S.A. Andersson, D. Madigan and M.D. Perlman, On the Markov equivalence of chain graphs, undirected graphs, and acyclic digraphs, Scand. J. Statist. 24 (1997) 81–102.
S.A. Andersson, D. Madigan and M.D. Perlman, A characterization of Markov equivalence classes for acyclic digraphs, Ann. Statist. (1997) (in press).
S.A. Andersson, D. Madigan, M.D. Perlman and C.M. Triggs, On the relation between conditional independence models determined by finite distributive lattices and by directed acyclic graphs, J. Statist. Planning and Inference 48 (1995) 25–46.
S.A. Andersson and M.D. Perlman, Lattice models for conditional independence in a multivariate normal distribution. Preprint (Institute of Mathematical Statistics, University of Copenhagen and Department of Statistics, University of Washington, 1988).
S.A. Andersson and M.D. Perlman, Lattice-ordered conditional independence models for missing data, Statist. Probability Letters 12 (1991) 465–486.
S.A. Andersson and M.D. Perlman, Lattice models for conditional independence in a multivariate normal distribution, Ann. Statist. 21 (1993) 1318–1358.
S.A. Andersson and M.D. Perlman, Normal linear models with lattice conditional independence restrictions, in: Multivariate Analysis and Its Applications, eds. T.W. Anderson, K.-T. Fang and I. Olkin, IMS Lecture Notes-Monograph Series, Vol. 24 (1994) pp. 97–110.
S.A. Andersson and M.D. Perlman, Testing lattice conditional independence models, J. Multivariate Analysis 53 (1995) 18–38.
S.A. Andersson and M.D. Perlman, Unbiasedness of the likelihood ratio test for lattice conditional independence models, J. Multivariate Analysis 53 (1995) 1–17.
S.A. Andersson and M.D. Perlman, Normal linear regression models with recursive graphical Markov structure, Submitted to J. Multivariate Analysis (1997).
J.R.S. Blair and B. Peyton, An introduction to chordal graphs and clique trees, in: Graph Theory and Sparse Matrix Computation, eds. A. George, J.R. Gilbert and J.W.H. Liu (Springer-Verlag, New York, 1993) pp. 1–29.
D.M. Chickering, A transformational characterization of equivalent Bayesian network structures, in: Uncertainty in Artificial Intelligence: Proceedings of the Eleventh Conference, eds. P. Besnard and S. Hanks (Morgan Kaufmann, San Francisco, 1995) pp. 87–98.
D.R. Cox and N. Wermuth, Multivariate Dependencies: Models, Analysis, and Interpretation (Chapman and Hall, London, 1996).
B.A. Davey and H.A. Priestley, Introduction to Lattices and Order (Cambridge U. Press, Cambridge, UK, 1990).
A.P. Dawid and S.L. Lauritzen, Hyper Markov laws in the statistical analysis of decomposable graphical models, Ann. Statist. 21 (1993) 1272–1317.
D. Edwards, Introduction to Graphical Modeling (Springer, New York, 1995).
M. Frydenberg, The chain graph Markov property, Scand. J. Statist. 17 (1990) 333–353.
F.V. Jensen, An Introduction to Bayesian Network (U. College London Press, London, 1996).
J.T.A. Koster, Markov properties of nonrecursive causal models, Ann. Statist. 24 (1996) 2148–2177.
S.L. Lauritzen, Graphical Models (Oxford University Press, Oxford, 1996).
S.L. Lauritzen, A.P. Dawid, B.N. Larsen and H.-G. Leimer, Independence properties of directed Markov fields, Networks 20 (1990) 491–505.
S.L. Lauritzen and D.J. Spiegelhalter, Local computations with probabilities on graphical structures and their application to expert systems (with discussion), J. Royal Statist. Soc., Series B 50 (1988) 157–224.
D. Madigan and A.E. Raftery, Model selection and accounting for model uncertainty in graphical models using Occam's window, J. Amer. Statist. Assoc. 89 (1994) 1535–1546.
C. Meek, Causal inference and causal explanation with background knowledge, in: Uncertainty in Artificial Intelligence: Proceedings of the Eleventh Conference, eds. P. Besnard and S. Hanks (Morgan Kaufmann, San Francisco, 1995) pp. 403–410.
R.E. Neapolitan, Probabilistic Reasoning in Expert Systems (Wiley, New York, 1990).
J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference (Morgan Kaufmann, San Mateo, CA, 1988).
M.D. Perlman and L. Wu, Lattice conditional independence models for missing data in contingency tables (1996) (in preparation).
B.W. Peyton, A. Pothen and X. Yuan, Partitioning a chordal graph into transitive subgraphs for parallel sparse triangular solution, Linear Algebra Appl. 192 (1993) 329–354.
D.J. Spiegelhalter, A.P. Dawid, S.L. Lauritzen and R.G. Cowell, Bayesian analysis in expert systems (with discussion), Statist. Science 8 (1993) 219–283.
D.J. Spiegelhalter and S.L. Lauritzen, Sequential updating of conditional probabilities on directed graphical structures, Networks 20 (1990) 579–605.
P. Spirtes, C. Glymour and R. Scheines, Causation, Prediction, and Search (Springer, New York, 1993).
T. Verma and J. Pearl, Equivalence and synthesis of causal models, in: Uncertainty in Artificial Intelligence: Proceedings of the Sixth Conference, eds. M. Henrion et al. (North-Holland, 1990) pp. 220–227.
T. Verma and J. Pearl, An algorithm for deciding if a set of observed independencies has a causal explanation, in: Uncertainty in Artificial Intelligence: Proceedings of the Eighth Conference, eds. D. Dubois et al. (Morgan Kaufmann, San Francisco, 1992) pp. 323–330.
N. Wermuth and N. Lauritzen, Graphical and recursive models for contingency tables, Biometrika 70 (1983) 537–552.
J.L. Whittaker, Graphical Models in Applied Multivariate Statistics (Wiley, New York, 1990).
S. Wright, Correlation and causation, J. Agricultural Research 20 (1921) 557–585.
J. York, D. Madigan, I. Heuch and R.T. Lie, Estimating a proportion of birth defects by double sampling: a Bayesian approach incorporating covariates and model uncertainty, Applied Statistics 44 (1995) 227–242.
A. Zellner, An efficient method of estimating seemingly unrelated regression equations and tests for aggregation bias, J. Amer. Statist. Assoc. 57 (1962) 348–368.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Andersson, S.A., Madigan, D., Perlman, M.D. et al. A graphical characterization of lattice conditional independence models. Annals of Mathematics and Artificial Intelligence 21, 27–50 (1997). https://doi.org/10.1023/A:1018901032102
Issue Date:
DOI: https://doi.org/10.1023/A:1018901032102