Let Y ∈ ℝn be a random vector with mean s and covariance matrix σ2PntPn where Pn is some known n × n-matrix. We construct a statistical procedure to estimate s as well as under moment condition on Y or Gaussian hypothesis. Both cases are developed for known or unknown σ2. Our approach is free from any prior assumption on s and is based on non-asymptotic model selection methods. Given some linear spaces collection {Sm, m ∈ ℳ}, we consider, for any m ∈ ℳ, the least-squares estimator ŝm of s in Sm. Considering a penalty function that is not linear in the dimensions of the Sm's, we select some m̂ ∈ ℳ in order to get an estimator ŝm̂ with a quadratic risk as close as possible to the minimal one among the risks of the ŝm's. Non-asymptotic oracle-type inequalities and minimax convergence rates are proved for ŝm̂. A special attention is given to the estimation of a non-parametric component in additive models. Finally, we carry out a simulation study in order to illustrate the performances of our estimators in practice.
Mots-clés : model selection, nonparametric regression, penalized criterion, oracle inequality, correlated data, additive regression, minimax rate
@article{PS_2014__18__77_0, author = {Gendre, Xavier}, title = {Model selection and estimation of a component in additive regression}, journal = {ESAIM: Probability and Statistics}, pages = {77--116}, publisher = {EDP-Sciences}, volume = {18}, year = {2014}, doi = {10.1051/ps/2012028}, mrnumber = {3143734}, language = {en}, url = {http://www.numdam.org/articles/10.1051/ps/2012028/} }
TY - JOUR AU - Gendre, Xavier TI - Model selection and estimation of a component in additive regression JO - ESAIM: Probability and Statistics PY - 2014 SP - 77 EP - 116 VL - 18 PB - EDP-Sciences UR - http://www.numdam.org/articles/10.1051/ps/2012028/ DO - 10.1051/ps/2012028 LA - en ID - PS_2014__18__77_0 ER -
Gendre, Xavier. Model selection and estimation of a component in additive regression. ESAIM: Probability and Statistics, Tome 18 (2014), pp. 77-116. doi : 10.1051/ps/2012028. http://www.numdam.org/articles/10.1051/ps/2012028/
[1] Statistical predictor identification. Ann. Inst. Stat. Math. 22 (1970) 203-217. | MR | Zbl
,[2] Choosing a penalty for model selection in heteroscedastic regression. Preprint arXiv:0812.3141v2 (2010).
,[3] Data-driven calibration of penalties for least-squares regression. J. Machine Learn. Research 10 (2009) 245-279.
and ,[4] Model selection for regression on a fixed design. Probab. Theory Related Fields 117 (2000) 467-493. | MR | Zbl
,[5] Model selection for regression on a random design. ESAIM: Probab. Statist. 6 (2002) 127-146. | Numdam | MR | Zbl
,[6] Adaptive estimation in autoregression or β-mixing regression via model selection. Ann. Stat. 29 (2001) 839-875. | MR | Zbl
, and ,[7] From model selection to adaptive estimation. Festschrift for Lucien Lecam: Research Papers in Probab. Stat. (1997) 55-87. | MR | Zbl
and ,[8] Minimum contrast estimators on sieves: exponential bounds and rates of convergence. Bernoulli 4 (1998) 329-375. | MR | Zbl
and ,[9] An adaptive compression algorithm in Besov spaces. Constr. Approx. 16 (2000) 1-36. | MR | Zbl
and ,[10] Gaussian model selection. J. Europ. Math. Soc. 3 (2001) 203-268. | MR | Zbl
and .[11] Minimal penalties for gaussian model selection. Probab. Theory Related Fields 138 (2007) 33-73. | MR | Zbl
and ,[12] Estimating optimal transformations for multiple regression and correlations (with discussion). J. Amer. Stat. Assoc. 80 (1985) 580-619. | MR | Zbl
and ,[13] Adaptive nonparametric regression estimation in presence of right censoring. Math. Methods Stat. 15 (2006) 233-255. | MR
and ,[14] Model selection for additive regression models in the presence of censoring, chapt. 1 in “Mathematical Methods in Survival Analysis, Reliability and Quality of Life”, Wiley (2008) 17-31. | MR
and ,[15] Linear smoothers and additive models (with discussion). Ann. Stat. 17 (1989) 453-555. | MR | Zbl
, and ,[16] Adaptive estimation of mean and volatility functions in (auto-)regressive models. Stoch. Process. Appl. 97 (2002) 111-145. | MR | Zbl
and ,[17] Simultaneous estimation of the mean and the variance in heteroscedastic gaussian regression. Electron. J. Stat. 2 (2008) 1345-1372. | MR
,[18] Nonparametric and Semiparametric Models. Springer (2004). | MR | Zbl
, , and .[19] Generalized additive models. Chapman and Hall (1990). | MR | Zbl
and ,[20] Matrix analysis. Cambridge University Press (1990). | MR | Zbl
and ,[21] Testing inverse problems: a direct or an indirect problem? J. Stat. Plann. Inference 141 (2011) 1849-1861. | MR
, and ,[22] Adaptive estimation of a quadratic functional by model selection. Ann. Stat. 28 (2000) 1302-1338. | MR | Zbl
and ,[23] Introduction to a theory of the internal structure of functional relationships. Econometrica 15 (1947) 361-373. | MR | Zbl
,[24] A kernel method of estimating structured nonparametric regression based on marginal integration. Biometrika 82 (1995) 93-101. | MR | Zbl
and ,[25] Some comments on cp. Technometrics 15 (1973) 661-675,. | Zbl
,[26] The existence and asymptotic properties of a backfitting projection algorithm under weak conditions. Ann. Stat. 27 (1999) 1443-1490. | MR | Zbl
, and ,[27] Concentration inequalities and model selection, in vol. 1896 of Lect. Notes Math. Lectures from the 33rd Summer School on Probability Theory held in Saint-Flour, July 6-23 (2003). Springer, Berlin (2007). | MR | Zbl
,[28] Regression and times series model selection. River Edge, NJ (1998). | MR | Zbl
and ,[29] High-dimensional additive modeling. Ann. Stat. 37 (2009) 3779-3821. | MR
, and ,[30] Fitting a bivariate additive model by local polynomial regression. Ann. Stat. 25 (1997) 186-211. | MR | Zbl
and ,[31] Limit theorems of probability theory: sequences of independent random variables. Oxford Studies Probab. 4 (1995). | MR | Zbl
,[32] Sparse additive models. J. Royal Statist. Soc. 71 (2009) 1009-1030. | MR
, , and ,[33] DNA, Words and Models. Cambridge University Press (2005). | MR | Zbl
, and ,[34] Multivariate locally weighted least squares regression. Ann. Stat. 22 (1994) 1346-1370. | MR | Zbl
and ,[35] The analysis of variance. Wiley-Interscience (1959). | Zbl
,[36] Estimation of derivatives for additive separable models. Statististics 33 (1999) 241-265. | MR | Zbl
and ,[37] Additive regression and other nonparametric models. Ann. Stat. 14 (1985) 590-606. | MR | Zbl
,[38] Nonparametric identification of nonlinear time series: Selecting significant lags. J. Amer. Stat. Assoc. 89 (1994) 1410-1430. | MR | Zbl
and ,[39] Inequalities for the rth absolute moment of a sum of random variables 1 ≤ r ≤ 2 . Ann. Math. Stat. 36 (1965) 299-303. | MR | Zbl
and ,Cité par Sources :