• Bernoulli
  • Volume 23, Number 2 (2017), 1102-1129.

Automorphism groups of Gaussian Bayesian networks

Jan Draisma and Piotr Zwiernik

Full-text: Access denied (no subscription detected)

We're sorry, but we are unable to provide you with the full text of this article because we are not able to identify you as a subscriber. If you have a personal subscription to this journal, then please login. If you are already logged in, then you may need to update your profile to register your subscription. Read more about accessing full-text


In this paper, we extend earlier work on groups acting on Gaussian graphical models to Gaussian Bayesian networks and more general Gaussian models defined by chain graphs with no induced subgraphs of the form $i\to j-k$. We fully characterise the maximal group of linear transformations which stabilises a given model and we provide basic statistical applications of this result. This includes equivariant estimation, maximal invariants for hypothesis testing and robustness. In our proof, we derive simple necessary and sufficient conditions on vanishing subminors of the concentration matrix in the model. The computation of the group requires finding the essential graph. However, by applying Stúdeny’s theory of imsets, we show that computations for DAGs can be performed efficiently without building the essential graph.

Article information

Bernoulli, Volume 23, Number 2 (2017), 1102-1129.

Received: January 2015
Revised: September 2015
First available in Project Euclid: 4 February 2017

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

chain graphs Gaussian graphical models group action equivariant estimator invariant test transformation family


Draisma, Jan; Zwiernik, Piotr. Automorphism groups of Gaussian Bayesian networks. Bernoulli 23 (2017), no. 2, 1102--1129. doi:10.3150/15-BEJ771.

Export citation


  • [1] Andersson, S.A., Madigan, D. and Perlman, M.D. (1997). A characterization of Markov equivalence classes for acyclic digraphs. Ann. Statist. 25 505–541.
  • [2] Andersson, S.A., Madigan, D. and Perlman, M.D. (2001). Alternative Markov properties for chain graphs. Scand. J. Stat. 28 33–85.
  • [3] Andersson, S.A. and Perlman, M.D. (2006). Characterizing Markov equivalence classes for AMP chain graph models. Ann. Statist. 34 939–972.
  • [4] Barndorff-Nielsen, O., Blæsild, P., Jensen, J.L. and Jørgensen, B. (1982). Exponential transformation models. Proc. Roy. Soc. London Ser. A 379 41–65.
  • [5] Berrington, A., Hu, Y., Smith, P.W.F. and Sturgis, P. (2008). A graphical chain model for reciprocal relationships between women’s gender role attitudes and labour force participation. J. Roy. Statist. Soc. Ser. A 171 89–108.
  • [6] Draisma, J., Kuhnt, S. and Zwiernik, P. (2013). Groups acting on Gaussian graphical models. Ann. Statist. 41 1944–1969.
  • [7] Draisma, J., Sullivant, S. and Talaska, K. (2013). Positivity for Gaussian graphical models. Adv. in Appl. Math. 50 661–674.
  • [8] Drton, M., Sturmfels, B. and Sullivant, S. (2009). Lectures on Algebraic Statistics. Oberwolfach Seminars 39. Basel: Birkhäuser.
  • [9] Drton, M. and Xiao, H. (2010). Smoothness of Gaussian conditional independence models. Contemp. Math. 516 155–177.
  • [10] Eaton, M.L. (1989). Group Invariance Applications in Statistics. NSF-CBMS Regional Conference Series in Probability and Statistics 1. Hayward, CA: IMS.
  • [11] Ferrándiz, J., Castillo, E.F. and Sanmartín, P. (2005). Temporal aggregation in chain graph models. J. Statist. Plann. Inference 133 69–93.
  • [12] Frydenberg, M. (1990). The chain graph Markov property. Scand. J. Stat. 17 333–353.
  • [13] Gessel, I.M. and Viennot, X.G. (1989). Determinants, paths, and plane partitions. Tech. report, Brandeis Univ.
  • [14] Gross, E. and Sullivant, S. (2014). The maximum likelihood threshold of a graph. Preprint. Available at arXiv:1404.6989.
  • [15] Lauritzen, S.L. (1996). Graphical Models. Oxford Statistical Science Series 17. New York: The Clarendon Press, Oxford Univ. Press.
  • [16] Lauritzen, S.L. and Richardson, T.S. (2002). Chain graph models and their causal interpretations. J. R. Stat. Soc. Ser. B. Stat. Methodol. 64 321–361.
  • [17] Lauritzen, S.L. and Wermuth, N. (1989). Graphical models for associations between variables, some of which are qualitative and some quantitative. Ann. Statist. 17 31–57.
  • [18] Lehmann, E.L. and Romano, J.P. (2005). Testing Statistical Hypotheses, 3rd ed. Springer Texts in Statistics. New York: Springer.
  • [19] Lněnička, R. and Matúš, F. (2007). On Gaussian conditional independent structures. Kybernetika (Prague) 43 327–342.
  • [20] Milan Studený, Hemmecke, R. and Lindner, S. (2010). Characteristic imset: A simple algebraic representative of a Bayesian network structure. In Proceedings of the 5th European Workshop on Probabilistic Graphical Models (P. Myllymäki, T. Roos and T. Jaakkola, eds.) 257–264. Helsinki Institute for Information Technology HIIT, Helsinki, Finland.
  • [21] Roverato, A. (2005). A unified approach to the characterization of equivalence classes of DAGs, chain graphs with no flags and chain graphs. Scand. J. Stat. 32 295–312.
  • [22] Studený, M. (2004). Characterization of essential graphs by means of the operation of legal merging of components: New trends in probabilistic graphical models. Internat. J. Uncertain. Fuzziness Knowledge-Based Systems 12 43–62.
  • [23] Studený, M. (2005). Probabilistic Conditional Independence Structures. Information Science and Statistics. London: Springer.
  • [24] Studený, M., Roverato, A. and Štěpánová, Š. (2009). Two operations of merging and splitting components in a chain graph. Kybernetika (Prague) 45 208–248.
  • [25] Studený, M. and Vomlel, J. (2009). A reconstruction algorithm for the essential graph. Internat. J. Approx. Reason. 50 385–413.
  • [26] Sullivant, S., Talaska, K. and Draisma, J. (2010). Trek separation for Gaussian graphical models. Ann. Statist. 38 1665–1685.
  • [27] Sun, D. and Sun, X. (2005). Estimation of the multivariate normal precision and covariance matrices in a star-shape model. Ann. Inst. Statist. Math. 57 455–484.
  • [28] Uhler, C. (2012). Geometry of maximum likelihood estimation in Gaussian graphical models. Ann. Statist. 40 238–261.
  • [29] Verma, T.S. and Pearl, J. (1990). Equivalence and Synthesis of Causal Models. In UAI ’90: Proceedings of the Sixth Annual Conference on Uncertainty in Artificial Intelligence (P.P. Bonissone, M. Henrion, L.N. Kanal and J.F. Lemmer, eds.) 27–29. Cambridge, MA: MIT.
  • [30] Wan Norsiah Mohamed, Diamond, I. and Smith, P.W.F. (1998). The determinants of infant mortality in Malaysia: A graphical chain modelling approach. J. Roy. Statist. Soc. Ser. A 161 349–366.