Unbiased risk estimation method for covariance estimation
ESAIM: Probability and Statistics, Tome 18 (2014) , pp. 251-264.

We consider a model selection estimator of the covariance of a random process. Using the Unbiased Risk Estimation (U.R.E.) method, we build an estimator of the risk which allows to select an estimator in a collection of models. Then, we present an oracle inequality which ensures that the risk of the selected estimator is close to the risk of the oracle. Simulations show the efficiency of this methodology.

DOI : https://doi.org/10.1051/ps/2013034
Classification : 62G05
Mots clés : covariance estimation, model selection, U.R.E. method
@article{PS_2014__18__251_0,
author = {Lescornel, H\'el\ene and Loubes, Jean-Michel and Chabriac, Claudie},
title = {Unbiased risk estimation method for covariance estimation},
journal = {ESAIM: Probability and Statistics},
pages = {251--264},
publisher = {EDP-Sciences},
volume = {18},
year = {2014},
doi = {10.1051/ps/2013034},
language = {en},
url = {http://archive.numdam.org/articles/10.1051/ps/2013034/}
}
Lescornel, Hélène; Loubes, Jean-Michel; Chabriac, Claudie. Unbiased risk estimation method for covariance estimation. ESAIM: Probability and Statistics, Tome 18 (2014) , pp. 251-264. doi : 10.1051/ps/2013034. http://archive.numdam.org/articles/10.1051/ps/2013034/`

[1] R.J. Adler, An introduction to continuity, extrema, and related topics for general gaussian processes. Lect. Note Ser. Institute of Mathematical Statistics (1990). | MR 1088478 | Zbl 0747.60039

[2] P.J. Bickel and E. Levina, Covariance regularization by thresholding. Ann. Statist. 36 (2008) 2577-2604. | MR 2485008 | Zbl 1196.62062

[3] J. Bigot, R. Biscay, J.-M. Loubes and L.M. Alvarez, Group lasso estimation of high-dimensional covariance matrices. J. Machine Learn. Res. (2011). | MR 2877598 | Zbl 1280.68156

[4] J. Bigot, R. Biscay, J.-M. Loubes and L. Muñiz-Alvarez, Nonparametric estimation of covariance functions by model selection. Electron. J. Statis. 4 (2010) 822-855. | MR 2684389

[5] J. Bigot, R. Biscay Lirio, J.-M. Loubes and L. Muniz Alvarez, Adaptive estimation of spectral densities via wavelet thresholding and information projection (2010).

[6] R. Biscay, L.M. Rodrguez and E. Daz-Frances, Cross-validation of covariance structures using the frobenius matrix distance as a discrepancy function. J. Stat. Comput. Simul. 58 (1997) 195-215. | Zbl 0880.62063

[7] T. Cai and M. Yuan, Nonparametric covariance function estimation for functional and longitudinal data. Technical report (2010).

[8] N.A.C. Cressie, Statistics for spatial data. Wiley Series in Probability and Mathematical Statistics: Applied Probability and Statistics. Revised reprint of the 1991 edition, A Wiley-Interscience Publication. John Wiley and Sons Inc., New York (1993). | MR 1239641 | Zbl 0799.62002

[9] P.J. Diggle and A.P. Verbyla, Nonparametric estimation of covariance structure in longitudinal data. Biometrics 54 (1998) 401-415. | Zbl 1058.62600

[10] A.G. Journel, Kriging in terms of projections. J. Int. Assoc. Math. Geol. 9 (1977) 563-586. | MR 456314

[11] C.R. Rao, Linear statistical inference and its applications. Wiley ser. Probab. Stastis. Wiley, 2nd edn. (1973). | MR 346957 | Zbl 0256.62002

[12] G.A.F. Seber, A matrix handbook for statisticians. Wiley ser. Probab. Stastis. Wiley (2008). | MR 2365265 | Zbl 1143.15001

[13] G.R. Shorack and J.A. Wellner, Empirical processes with applications to statistics. Wiley (1986). | MR 838963 | Zbl 1170.62365

[14] C.M. Stein, Estimation of the mean of a multivariate normal distribution. Ann. Statis. 9 (1981) 1135-1151. | MR 630098 | Zbl 0476.62035

[15] M.L. Stein. Interpolation of spatial data. Some theory for Kriging. Springer Ser. Statis. Springer-Verlag, New York (1999). | MR 1697409 | Zbl 0924.62100

[16] A.B. Tsybakov, Introduction à l'estimation non-paramétrique. Vol. 41 of Math. Appl. Springer (2004). | MR 2013911 | Zbl 1029.62034