We propose a method based on a penalised likelihood criterion, for estimating the number on non-zero components of the mean of a gaussian vector. Following the work of Birgé and Massart in gaussian model selection, we choose the penalty function such that the resulting estimator minimises the Kullback risk.
Mots clés : Kullback risk, model selection, penalised likelihood criteria
@article{PS_2006__10__164_0, author = {Huet, Sylvie}, title = {Model selection for estimating the non zero components of a gaussian vector}, journal = {ESAIM: Probability and Statistics}, pages = {164--183}, publisher = {EDP-Sciences}, volume = {10}, year = {2006}, doi = {10.1051/ps:2006004}, mrnumber = {2218407}, language = {en}, url = {http://www.numdam.org/articles/10.1051/ps:2006004/} }
TY - JOUR AU - Huet, Sylvie TI - Model selection for estimating the non zero components of a gaussian vector JO - ESAIM: Probability and Statistics PY - 2006 SP - 164 EP - 183 VL - 10 PB - EDP-Sciences UR - http://www.numdam.org/articles/10.1051/ps:2006004/ DO - 10.1051/ps:2006004 LA - en ID - PS_2006__10__164_0 ER -
Huet, Sylvie. Model selection for estimating the non zero components of a gaussian vector. ESAIM: Probability and Statistics, Tome 10 (2006), pp. 164-183. doi : 10.1051/ps:2006004. http://www.numdam.org/articles/10.1051/ps:2006004/
[1] Adapting to unknown sparsity by controlloing the false discovery rate. Technical Report 2000-19, Department of Statistics, Stanford University (2000). | Zbl
, , and ,[2] Information theory and an extension of the maximum likelihood principle, in 2nd International Symposium on Information Theory, B.N. Petrov and F. Csaki Eds., Budapest Akademia Kiado (1973) 267-281. | Zbl
,[3] A bayesian analysis of the minimum aic procedure. Ann. Inst. Statist. Math. 30 (1978) 9-14. | Zbl
,[4] Model selection using wavelet decomposition and applications. Biometrika 84 (1997) 751-763. | Zbl
, and ,[5] Adaptive tests of qualitative hypotheses. ESAIM: PS 7 (2003) 147-159. | Numdam | Zbl
, and ,[6] Risk bounds for model selection via penalization. Probab. Theory Rel. Fields 113 (1999) 301-413. | Zbl
, and ,[7] Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. R. Statist. Soc. B 57 (1995) 289-300. | Zbl
and ,[8] Gaussian model selection. J. Eur. Math. Soc. (JEMS) 3 (2001) 203-268. | Zbl
and ,[9] A generalized cp criterion for gaussian model selection. Technical report, Univ. Paris 6, Paris 7, Paris (2001). | MR
and ,[10] Norm of gaussian sample function, in Proceedings of the 3rd Japan-URSS. Symposium on Probability Theory, Berlin, Springer-Verlag. Springer Lect. Notes Math. 550 (1976) 20-41. | Zbl
, and ,[11] Order Statistics. Wiley series in Probability and mathematical Statistics. John Wiley and Sons, NY (1981). | MR | Zbl
,[12] An analysis for unreplicated fractional factorials. Technometrics 28 (1986) 11-18. | Zbl
and ,[13] Adaptive variable selection competes with bayes expert. Technical report, The Wharton School of the University of Pennsylvania, Philadelphia (2002).
and ,[14] Comparison of methods for estimating the non zero components of a gaussian vector. Technical report, INRA, MIA-Jouy, www.inra.fr/miaj/apps/cgi-bin/raptech.cgi (2005).
,[15] Regression and time series model selection in small samples. Biometrika 76 (1989) 297-307. | Zbl
and ,[16] Empirical bayes selection of wavelet thresholds. Available from www.stats.ox.ac.uk/ silverma/papers.html (2003). | Zbl
and ,[17] Adaptive estimation of a quadratic functional by model selection. Ann. Statist. 28 (2000) 1302-1338. | Zbl
and ,[18] Maximum likelihood principle and model selection when the true model is unspecified. J. Multivariate Anal. 27 (1988) 392-403. | Zbl
,[19] Inference for effect-saturated fractional factorials. Technometrics 37 (1995) 82-93. | Zbl
and ,[20] Universal coding, information, prediction and estimation. IEEE Trans. Infor. Theory 30 (1984) 629-636. | Zbl
,[21] Quick and easy analysis of unreplicated factorials. Technometrics 31(4) (1989) 469-473.
,[22] Estimating the dimension of a model. Ann. Statist. 6 (1978) 461-464. | Zbl
,Cité par Sources :