# zbMATH — the first resource for mathematics

Flexible covariance estimation in graphical Gaussian models. (English) Zbl 1168.62054
Summary: We propose a class of Bayes estimators for the covariance matrix of graphical Gaussian models being Markov with respect to a decomposable graph $$G$$. Working with the $$W_{P_G}$$ family, defined by G. Letac and H. Massam [Ann. Stat. 35, No. 3, 1278–1323 (2007; Zbl 1194.62078)], we derive closed-form expressions for Bayes estimators under the entropy and squared-error losses. The $$W_{P_G}$$ family includes the classical inverse of the hyper inverse Wishart but has many more shape parameters, thus allowing for flexibility in differentially shrinking various parts of the covariance matrix. Moreover, using this family avoids recourse to MCMC, often infeasible in high-dimensional problems. We illustrate the performance of our estimators through a collection of numerical examples where we explore frequentist risk properties and the efficacy of graphs in the estimation of high-dimensional covariance structures.

##### MSC:
 62H12 Estimation in multivariate analysis 62C10 Bayesian problems; characterization of Bayes procedures 05C90 Applications of graph theory 62F15 Bayesian inference
##### Keywords:
Bayes estimators; shrinkage; regularization
HdBCS
Full Text:
##### References:
 [1] Bernardo, J. M. (1979). Reference posterior distributions for Bayesian inference. J. Roy. Statist. Soc. Ser. B 41 113-147. JSTOR: · Zbl 0428.62004 [2] Bickel, P. and Levina, E. (2008). Regularized estimation of large covariance matrices. Ann. Statist. 36 199-227. · Zbl 1132.62040 [3] Carvalho, C. M., Massam, H. and West, M. (2007). Simulation of hyper-inverse- Wishart distributions in graphical models. Biometrika 94 647-659. · Zbl 1135.62011 [4] Chen, C. (1979). Bayesian inference for a normal dispersion matrix and its application to stochastic multiple regression analysis. J. Roy. Statist. Soc. Ser. B 41 235-248. JSTOR: · Zbl 0418.62024 [5] Clarke, B. and Barron, A. (1990). Information-theoretic asymptotics of Bayes methods. IEEE Trans. Inform. Theory 36 453-471. · Zbl 0709.62008 [6] Clarke, B. and Yuan, A. (2004). Partial information reference priors: derivation and interpretations. J. Statist. Plann. Inference 123 313-345. · Zbl 1053.62010 [7] Consonni, G. and Veronese, P. (2003). Enriched conjugate and reference priors for the Wishart family on the symmetric cones. Ann. Statist. 31 1491-1516. · Zbl 1046.62054 [8] Daniels, M. and Kass, R. (1999). Nonconjugate Bayesian estimation of covariance matrices and its use in hierarchical models. J. Amer. Statist. Assoc. 94 1254-1263. JSTOR: · Zbl 1069.62508 [9] Daniels, M. and Kass, R. (2001). Shrinkage estimators for covariance matrices. Biometrics 57 1173-1184. JSTOR: · Zbl 1209.62132 [10] Datta, G. and Ghosh, M. (1995). Some remarks on noninformative priors. J. Amer. Statist. Assoc. 90 1357-1363. JSTOR: · Zbl 0878.62003 [11] Dawid, A. P. and Lauritzen, S. L. (1993). Hyper-Markov laws in the statistical analysis of decomposable graphical models. Ann. Statist. 21 1272-317. · Zbl 0815.62038 [12] Dempster, A. (1972). Covariance selection. Biometrics 28 157-175. [13] Diaconis, P. and Ylvisaker, D. (1979). Conjugate priors for exponential families. Ann. Statist. 7 269-281. · Zbl 0405.62011 [14] Gröne, R., Johnson, C. R., Sà, E. M. and Wolkowicz, H. (1984). Positive definite completions of partial Hermitian matrices. Linear Algebra Appl. 58 109-124. · Zbl 0547.15011 [15] Haff, L. R. (1977). Minimax estimators for a multinormal precision matrix. J. Multivariate Anal. 7 374-385. · Zbl 0402.62028 [16] Haff, L. R. (1980). Empirical Bayes estimation of the multivariate normal covariance matrix. Ann. Statist. 8 586-597. · Zbl 0441.62045 [17] Haff, L. R. (1991). The variational form of certain Bayes estimators. Ann. Statist. 19 1163-1190. · Zbl 0739.62046 [18] Huang, J. Liu, N., Pourahmadi, M. and Liu, L. (2006). Covariance matrix selection and estimation via penalised normal likelihood. Biometrika 93 85-98. · Zbl 1152.62346 [19] James, W. and Stein, C. (1961). Estimation with quadratic loss. Proc. Fourth Berkeley Symp. Math. Statist. Probab. (J. Neyman, ed.) 1 361-379. Univ. California Press, Berkeley. · Zbl 1281.62026 [20] Jefferys, W. and Berger, J. (1992). Ockham’s razor and Bayesian analysis. American Scientist 80 64-72. [21] Jones, B., Carvalho, C., Dobra, A., Hans, C., Carter, C. and West, M. (2005). Experiments in stochastic computation for high-dimensional graphical models. Statist. Sci. 20 388-400. · Zbl 1130.62408 [22] Krishnamoorthy, K. (1991). Estimation of normal covariance and precision matrices with incomplete data. Comm. Statist. Theory Methods 20 757-770. · Zbl 0724.62059 [23] Krishnamoorthy, K. and Gupta, A. (1989). Improved minimax estimation of a normal precision matrix. Canad. J. Statist. 17 91-102. JSTOR: · Zbl 0678.62060 [24] Lauritzen, S. L. (1996). Graphical Models . Clarendon Press, Oxford. · Zbl 0907.62001 [25] Ledoit, O. and Wolf, M. (2004). A well conditioned estimator for large-dimensional covariance matrices. J. Multivariate Anal. 88 365-411. · Zbl 1032.62050 [26] Leonard, T. and Hsu, J. S. J. (1992). Bayesian inference for a covariance matrix. Ann. Statist. 20 1669-1696. · Zbl 0765.62031 [27] Letac, G. and Massam, H. (2007). Wishart distributions for decomposable graphs. Ann. Statist. 35 1278-1323. · Zbl 1194.62078 [28] Leung, P. and Muirhead, R. (1987). Estimation of parameter matrices and eigenvalues in MANOVA and canonical correlation analysis. Ann. Statist. 15 1651-1666. · Zbl 0629.62059 [29] Lin, S. and Perlman, M. (1985). A Monte Carlo comparison of four estimators of a covariance matrix. In Multivariate Analysis VI (P. R. Krishnaiah, ed.) 411-429. North Holland, Amsterdam. · Zbl 0593.62051 [30] Meinshausen, N. and Buhlmann, P. (2006). High-dimensional graphs and variable selection with the Lasso. Ann. Statist. 34 1436-1462. · Zbl 1113.62082 [31] Muirhead, R. J. (1982). Aspects of Multivariate Statistical Theory . Wiley, New York. · Zbl 0556.62028 [32] Roverato, A. (2000). Cholesky decomposition of a hyper inverse Wishart matrix. Biometrika 87 99-112. JSTOR: · Zbl 0974.62047 [33] Sharma, D. and Krishnamoorthy, K. (1985). Empirical Bayes estimators of normal covariance matrix. Sankhyā Ser. A 47 247-254. · Zbl 0588.62077 [34] Stein, C. (1956). Some problems in multivariate analysis. Technical Report No. 6, Univ. Stanford. · Zbl 0073.35602 [35] Stein, C. (1975). Estimation of a covariance matrix. In Rietz Lecture. 39th Annual Meeting . IMS, Atlanta, GA. · Zbl 0302.05015 [36] Whittaker, J. (1990). Graphical Models in Applied Multivariate Statistics . Wiley, Chichester. · Zbl 0732.62056 [37] Yang, R. and Berger, J. O. (1994). Estimation of a covariance matrix using the reference prior. Ann. Statist. 22 1195-1211. · Zbl 0819.62013
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.