The Annals of Statistics

Wishart distributions for decomposable graphs

Gérard Letac and Hélène Massam

Full-text: Open access

Abstract

When considering a graphical Gaussian model ${\mathcal{N}}_{G}$ Markov with respect to a decomposable graph G, the parameter space of interest for the precision parameter is the cone PG of positive definite matrices with fixed zeros corresponding to the missing edges of G. The parameter space for the scale parameter of ${\mathcal{N}}_{G}$ is the cone QG, dual to PG, of incomplete matrices with submatrices corresponding to the cliques of G being positive definite. In this paper we construct on the cones QG and PG two families of Wishart distributions, namely the Type I and Type II Wisharts. They can be viewed as generalizations of the hyper Wishart and the inverse of the hyper inverse Wishart as defined by Dawid and Lauritzen [Ann. Statist. 21 (1993) 1272–1317]. We show that the Type I and II Wisharts have properties similar to those of the hyper and hyper inverse Wishart. Indeed, the inverse of the Type II Wishart forms a conjugate family of priors for the covariance parameter of the graphical Gaussian model and is strong directed hyper Markov for every direction given to the graph by a perfect order of its cliques, while the Type I Wishart is weak hyper Markov. Moreover, the inverse Type II Wishart as a conjugate family presents the advantage of having a multidimensional shape parameter, thus offering flexibility for the choice of a prior.

Both Type I and II Wishart distributions depend on multivariate shape parameters. A shape parameter is acceptable if and only if it satisfies a certain eigenvalue property. We show that the sets of acceptable shape parameters for a noncomplete G have dimension equal to at least one plus the number of cliques in G. These families, as conjugate families, are richer than the traditional Diaconis–Ylvisaker conjugate families which all have a shape parameter set of dimension one. A decomposable graph which does not contain a three-link chain as an induced subgraph is said to be homogeneous. In this case, our Wisharts are particular cases of the Wisharts on homogeneous cones as defined by Andersson and Wojnar [J. Theoret. Probab. 17 (2004) 781–818] and the dimension of the shape parameter set is even larger than in the nonhomogeneous case: it is indeed equal to the number of cliques plus the number of distinct minimal separators. Using the model where G is a three-link chain, we show by computing a 7-tuple integral that in general we cannot expect the shape parameter sets to have dimension larger than the number of cliques plus one.

Article information

Source
Ann. Statist., Volume 35, Number 3 (2007), 1278-1323.

Dates
First available in Project Euclid: 24 July 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1185304006

Digital Object Identifier
doi:10.1214/009053606000001235

Mathematical Reviews number (MathSciNet)
MR2341706

Zentralblatt MATH identifier
1194.62078

Subjects
Primary: 62H99: None of the above, but in this section
Secondary: 62E15: Exact distribution theory

Keywords
Graphical models covariance selection models hyper Markov conjugate priors perfect order triangulated graphs chordal graphs inverse Wishart hyper Wishart and hyper inverse Wishart homogeneous cones natural exponential families

Citation

Letac, Gérard; Massam, Hélène. Wishart distributions for decomposable graphs. Ann. Statist. 35 (2007), no. 3, 1278--1323. doi:10.1214/009053606000001235. https://projecteuclid.org/euclid.aos/1185304006


Export citation

References

  • Abramowitz, M. and Stegun, I. A., eds. (1965). Handbook of Mathematical Functions. U.S. Government Printing Office, Washington.
  • Andersson, S. A. (1999). Private communication.
  • Andersson, S. A. and Wojnar, G. G. (2004). Wishart distributions on homogeneous cones. J. Theoret. Probab. 17 781--818.
  • Barndorff-Nielsen, O. (1978). Information and Exponential Families in Statistical Theory. Wiley, Chichester.
  • Consonni, G. and Veronese, P. (2001). Conditionally reducible natural exponential families and enriched conjugate priors. Scand. J. Statist. 28 377--406.
  • Consonni, G. and Veronese, P. (2003). Enriched conjugate and reference priors for the Wishart family on symmetric cones. Ann. Statist. 31 1491--1516.
  • Dawid, A. and Lauritzen, S. L. (1993). Hyper-Markov laws in the statistical analysis of decomposable graphical models. Ann. Statist. 21 1272--1317.
  • Dempster, A. P. (1972). Covariance selection. Biometrics 28 157--175.
  • Diaconis, P. and Ylvisaker, D. (1979). Conjugate priors for exponential families. Ann. Statist. 7 269--281.
  • Gröne, R., Johnson, C. R., de Sá, E. and Wolkowicz, H. (1984). Positive definite completions of partial Hermitian matrices. Linear Algebra Appl. 58 109--124.
  • Lauritzen, S. L. (1996). Graphical Models. Oxford Univ. Press.
  • Letac, G. and Massam, H. (2006). Extremal rays and duals for cones of positive definite matrices with prescribed zeros. Linear Algebra Appl. 418 737--750.
  • Massam, H. and Neher, E. (1997). On transformations and determinants of Wishart variables on symmetric cones. J. Theoret. Probab. 10 867--902.
  • Muirhead, R. (1982). Aspects of Multivariate Statistical Theory. Wiley, New York.
  • Olkin, I. and Rubin, H. (1964). Multivariate beta distributions and independence properties of the Wishart distribution. Ann. Math. Statist. 35 261--269.
  • Roverato, A. (2000). Cholesky decomposition of a hyper inverse Wishart matrix. Biometrika 87 99--112.
  • Shanbag, D. N. (1988). The Davidson-Kendall problem and related results on the structure of the Wishart distribution. Austral. J. Statist. 30A 272--280.
  • Whittaker, J. (1990). Graphical Models in Applied Multivariate Statistics. Wiley, Chichester.