×

Robust estimator of the correlation matrix with sparse Kronecker structure for a high-dimensional matrix-variate. (English) Zbl 1437.62198

The estimation of the correlation matrix of a higher-dimensional matrix-variate \(X \in \mathbb{R}^{p\times q}\) is needed in practice many times. The authors propose a robust estimator based on Kendall’s correlation. The proposed estimator is extended further to tensor data. In this paper, it is shown that the Kronecker structure actually increases the effective sample size and leads to a fast convergence rate. They apply the method to Aries of GeneExpression in the Monse Aging (AGEMAP) database to investigate the behaviour of the proposed method.

MSC:

62H12 Estimation in multivariate analysis
62P10 Applications of statistics to biology and medical sciences; meta analysis
62G35 Nonparametric robustness
62H22 Probabilistic graphical models
62H35 Image analysis in multivariate analysis

Software:

Knorm; limma; ROCKET
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Barber, R. F.; Kolar, M., Rocket: Robust confidence intervals via Kendall’s tau for transelliptical graphical models, Ann. Statist., 46, 6B, 3422-3450 (2018) · Zbl 1410.62059
[2] Bergsma, W.; Dassios, A., A consistent test of independence based on a sign covariance related to Kendall’s tau, Bernoulli, 20, 2, 1006-1028 (2014) · Zbl 1400.62091
[3] Bickel, P. J.; Levina, E., Regularized estimation of large covariance matrices, Ann. Statist., 36, 1, 199-227 (2008) · Zbl 1132.62040
[4] Cui, Y.; Leng, C.; Sun, D., Sparse estimation of high-dimensional correlation matrices, Comput. Statist. Data Anal., 93, C, 390-403 (2016) · Zbl 1468.62044
[5] Dutilleul, P., The mle algorithm for the matrix normal distribution, J. Statist. Comput. Simul., 64, 2, 105-123 (1999) · Zbl 0960.62056
[6] Fox, M. D.; Raichle, M. E., Spontaneous fluctuations in brain activity observed with functional magnetic resonance imaging., Nat. Rev. Neurosci., 8, 9, 700-711 (2007)
[7] Gupta, A. K.; Nagar, D. K., Matrix Variate Distributions, Vol. 104 (1999), CRC Press
[8] Han, F.; Liu, H., Scale-invariant sparse PCA on high dimensional meta-elliptical data., J. Amer. Statist. Assoc., 109, 505, 275-287 (2014) · Zbl 1367.62185
[9] Han, F.; Liu, H., Statistical analysis of latent generalized correlation matrix estimation in transelliptical distribution, Bernoulli, 23, 1, 23-57 (2017) · Zbl 1359.62186
[10] He, S.; Yin, J.; Li, H.; Wang, X., Graphical model selection and estimation for high dimensional tensor data., J. Multivariate Anal., 128, 7, 165-185 (2014) · Zbl 1352.62081
[11] Hoff, P. D., Separable covariance arrays via the Tucker product, with applications to multivariate relational data, Bayesian Anal., 6, 2, 179-196 (2011) · Zbl 1330.62132
[12] Huffer, F. W.; Park, C., A test for elliptical symmetry, J. Multivariate Anal., 98, 2, 256-281 (2007) · Zbl 1105.62063
[13] Hung, H.; Wang, C.-C., Matrix variate logistic regression model with application to EEG data, Biostatistics, 14, 1, 189-202 (2012)
[14] Kong, D.; An, B.; Zhang, J.; Zhu, H., L2rm: Low-rank linear regression models for high-dimensional matrix responses, J. Amer. Statist. Assoc., just-accepted, 1-55 (2018)
[15] Leng, C.; Pan, G., Covariance estimation via sparse Kronecker structures, Bernoulli, 24, 4B, 3833-3863 (2018) · Zbl 1415.62033
[16] Leng, C.; Tang, C. Y., Sparse matrix graphical models, J. Amer. Statist. Assoc., 107, 499, 1187-1200 (2012) · Zbl 1443.62194
[17] Li, B.; Kim, M. K.; Altman, N., On dimension folding of matrix-or array-valued statistical objects, Ann. Statist., 38, 2, 1094-1121 (2010) · Zbl 1183.62091
[18] Li, G.; Peng, H.; Zhang, J.; Zhu, L., Robust rank correlation based screening, Ann. Statist., 40, 3, 1846-1877 (2010) · Zbl 1257.62067
[19] Li, M.; Yuan, B., 2d-lda: A statistical linear discriminant analysis for image matrix, Pattern Recognit. Lett., 26, 5, 527-532 (2005)
[20] Liu, H.; Han, F.; Yuan, M.; Lafferty, J.; Wasserman, L., High dimensional semiparametric Gaussian copula graphical models, Ann. Statist., 40, 4, 2293-2326 (2012) · Zbl 1297.62073
[21] Manzotti, A.; Preéz, F. J.; Quiroz, A. J., A statistic for testing the null hypothesis of elliptical symmetry, J. Multivariate Anal., 81, 2, 274-285 (2002) · Zbl 1011.62046
[22] Medland, S. E.; Jahanshad, N.; Neale, B. M.; Thompson, P. M., Whole-genome analyses of whole-brain data: working within an expanded search space, Nature Neurosci., 17, 6, 791 (2014)
[23] Ning, Y.; Liu, H., High-dimensional semiparametric bigraphical models, Biometrika, 100, 3, 655-670 (2013) · Zbl 1284.62327
[24] Niu, L.; Zhao, J., High dimensional semiparametric estimate of latent covariance matrix for matrix-variate, Statictica Sin., accepted (2017)
[25] Scharinger, C.; Rabl, U.; Sitte, H. H.; Pezawas, L., Imaging genetics of mood disorders, Neuroimage, 53, 3, 810-821 (2010)
[26] Schott, J. R., Testing for elliptical symmetry in covariance-matrix-based analyses, Statist. Probab. Lett., 60, 4, 395-404 (2002) · Zbl 1045.62051
[27] Sejnowski, T.; Makeig, S.; Delorme, A., Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis, Neuroimage, 34, 34, 1443-1449 (2007)
[28] Serfling, R. J., Approximation Theorems of Mathematical Statistics, Vol. 162 (2009), John Wiley & Sons
[29] Smyth, G. K., Limma: Linear models for microarray data, Bioinform. Comput. Biol. Sol. Using R Biocond., 397-420 (2011)
[30] Teng, S. L.; Huang, H., A statistical framework to infer functional gene relationships from biologically interrelated microarray experiments, J. Amer. Statist. Assoc., 104, 486, 465-473 (2009) · Zbl 1388.62335
[31] Thompson, P. M.; Ge, T.; Glahn, D. C.; Jahanshad, N.; Nichols, T. E., Genetics of the connectome, Neuroimage, 80, 475-488 (2013)
[32] Tsiligkaridis, T.; Hero, A. O., Covariance estimation in high dimensions via Kronecker product expansions, IEEE Trans. Signal Process., 61, 21, 5347-5360 (2013)
[33] Tsiligkaridis, T.; Hero I. I.I., A. O.; Zhou, S., Convergence properties of Kronecker graphical lasso algorithms (2012), arXiv preprint arXiv:1204.0585
[34] Vershynin, R., Introduction to the non-asymptotic analysis of random matrices (2015), Eprint Arxiv
[35] Wallbacks, L.; Norden, U. E.B., Multivariate data analysis of in situ pulp kinetics using 13 c cp/mas nmr, J. Wood Chem. Technol., 9, 2, 235-249 (2006)
[36] Werner, K.; Jansson, M.; Stoica, P., On estimation of covariance matrices with Kronecker product structure, IEEE Trans. Signal Process., 56, 2, 478-491 (2008) · Zbl 1390.94472
[37] Yin, J.; Li, H., Model selection and estimation in the matrix normal graphical model, J. Multivariate Anal., 107, 3, 119-140 (2012) · Zbl 1236.62058
[38] Zahn, J. M.; Poosala, S.; Owen, A. B.; Ingram, D. K.; Lustig, A.; Carter, A.; Weeraratna, A. T.; Taub, D. D.; Gorospe, M.; Mazanmamczarz, K., Agemap: A gene expression database for aging in mice, PLoS Genet., 3, 11, Article e201 pp. (2007)
[39] Zhou, H.; Li, L., Regularized matrix regression, J. R. Stat. Soc. Ser. B Stat. Methodol., 76, 2, 463-483 (2014) · Zbl 07555458
[40] Zhu, L. X.; Neuhaus, G., Conditional tests for elliptical symmetry, J. Multivariate Anal., 84, 2, 284-298 (2003) · Zbl 1014.62066
[41] Zou, H., The adaptive lasso and its oracle properties, Publ. Amer. Statist. Assoc., 101, 476, 1418-1429 (2006) · Zbl 1171.62326
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.