Model selection and estimation in the matrix normal graphical model

Motivated by analysis of gene expression data measured over different tissues or over time, we consider matrix-valued random variable and matrix-normal distribution, where the precision matrices have a graphical interpretation for genes and tissues, respectively. We present a l(1) penalized likelihood method and an efficient coordinate descent-based computational algorithm for model selection and estimation in such matrix normal graphical models (MNGMs). We provide theoretical results on the asymptotic distributions, the rates of convergence of the estimates and the sparsistency, allowing both the numbers of genes and tissues to diverge as the sample size goes to infinity. Simulation results demonstrate that the MNGMs can lead to better estimate of the precision matrices and better identifications of the graph structures than the standard Gaussian graphical models. We illustrate the methods with an analysis of mouse gene expression data measured over ten different tissues.

[1]  P. Dutilleul.  The mle algorithm for the matrix normal distribution , 1999 .

[2]  Genevera I. Allen,et al.  TRANSPOSABLE REGULARIZED COVARIANCE MODELS WITH AN APPLICATION TO MISSING DATA IMPUTATION. , 2009, The annals of applied statistics.

[3]  Robert Tibshirani,et al.  Inference with transposable data: modelling the effects of row and column correlations , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[4]  A. Dawid.  Some matrix-variate distribution theory: Notational considerations and a Bayesian application , 1981 .

[5]  M. West,et al.  Bayesian analysis of matrix normal graphical models. , 2009, Biometrika.

[6]  Jianqing Fan,et al.  Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties , 2001 .

[7]  Mike Rees,et al.  5. Statistics for Spatial Data , 1993 .

[8]  M. Yuan,et al.  Model selection and estimation in the Gaussian graphical model , 2007 .

[9]  N. H. Timm.  2 Multivariate analysis of variance of repeated measurements , 1980 .

[10]  T. Cai,et al.  A Constrained ℓ1 Minimization Approach to Sparse Precision Matrix Estimation , 2011, 1102.2233.

[11]  M. Genton,et al.  A likelihood ratio test for separability of covariances , 2006 .

[12]  Jianqing Fan,et al.  Sparsistency and Rates of Convergence in Large Covariance Matrix Estimation. , 2007, Annals of statistics.

[13]  Omkar Muralidharan,et al.  Detecting column dependence when rows are correlated and estimating the strength of the row correlation , 2010 .

[14]  Hongzhe Li,et al.  Gradient directed regularization for sparse Gaussian concentration graphs, with applications to inference of genetic networks. , 2006, Biostatistics.

[15]  N. Meinshausen,et al.  High-dimensional graphs and variable selection with the Lasso , 2006, math/0608017.

[16]  Adam J. Rothman,et al.  Generalized Thresholding of Large Covariance Matrices , 2009 .

[17]  Terence Tao,et al.  The Dantzig selector: Statistical estimation when P is much larger than n , 2005, math/0506081.

[18]  Peter D. Hoff,et al.  Separable covariance arrays via the Tucker product, with applications to multivariate relational data , 2010, 1008.2169.

[19]  H. Zou.  The Adaptive Lasso and Its Oracle Properties , 2006 .

[20]  P. Bickel,et al.  Regularized estimation of large covariance matrices , 2008, 0803.1909.

[21]  Ming Yuan,et al.  High Dimensional Inverse Covariance Matrix Estimation via Linear Programming , 2010, J. Mach. Learn. Res..

[22]  Haiyan Huang,et al.  A Statistical Framework to Infer Functional Gene Relationships From Biologically Interrelated Microarray Experiments , 2009 .

[23]  Bin Yu,et al.  High-dimensional covariance estimation by minimizing ℓ1-penalized log-determinant divergence , 2008, 0811.3628.

[24]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the graphical lasso. , 2008, Biostatistics.

[25]  Katherine Holmes,et al.  Vascular endothelial growth factor receptor-2: structure, function, intracellular signalling and therapeutic inhibition. , 2007, Cellular signalling.

[26]  Alexandre d'Aspremont,et al.  Model Selection Through Sparse Max Likelihood Estimation Model Selection Through Sparse Maximum Likelihood Estimation for Multivariate Gaussian or Binary Data , 2022 .

[27]  J. Finn.  A General Model for Multivariate Analysis , 1978 .

[28]  A. Owen,et al.  AGEMAP: A Gene Expression Database for Aging in Mice , 2007, PLoS genetics.

[29]  Lourens J. Waldorp,et al.  Spatiotemporal EEG/MEG source analysis based on a parametric noise covariance model , 2002, IEEE Transactions on Biomedical Engineering.

[30]  F. Graybill,et al.  Matrices with Applications in Statistics. , 1984 .

[31]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[32]  E. L. Lehmann,et al.  Theory of point estimation , 1950 .

[33]  Jeff G. Schneider,et al.  Learning Multiple Tasks with a Sparse Matrix-Normal Penalty , 2010, NIPS.

[34]  B. Efron.  Are a set of microarrays independent of each other? , 2009, The annals of applied statistics.

[35]  Jianqing Fan,et al.  NETWORK EXPLORATION VIA THE ADAPTIVE LASSO AND SCAD PENALTIES. , 2009, The annals of applied statistics.

[36]  Vwani P. Roychowdhury,et al.  Covariance selection for nonchordal graphs via chordal embedding , 2008, Optim. Methods Softw..