Adaptive nonparametric estimation in the functional linear model with functional output

被引:0
作者
Chagny, Gaelle [1 ]
Meynaoui, Anouar [2 ]
Roche, Angelina [3 ]
机构
[1] Univ Rouen Normandie, CNRS, LMRS, UMR 6085, F-76000 Rouen, France
[2] Univ Rennes 2, CNRS, IRMAR, F-35000 Rennes, France
[3] Univ Paris Cite, CNRS, MAP5, F-75006 Paris, France
关键词
Function data analysis; functional linear regression; adaptive estimation; minimax rates; CUMULATIVE DISTRIBUTION FUNCTION; REGRESSION; PREDICTION; SELECTION; MINIMAX; BOUNDS; RATES;
D O I
10.1214/25-EJS2400
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this paper, we consider a functional linear regression model, where both the covariate and the response variable are functional random variables. We address the problem of optimal nonparametric estimation of the conditional expectation operator in this model. A collection of projection estimators over finite dimensional subspaces is first introduce. We provide a non-asymptotic bias-variance decomposition for the Mean Square Prediction error in the case where these subspaces are generated by the (empirical) PCA functional basis. The automatic trade-off is realized thanks to a model selection device which selects the best projection dimensions: the penalized contrast estimator satisfies an oracle-type inequality and is thus optimal in an adaptive point of view. These upper-bounds allow us to derive convergence rates over ellipsoidal smoothness spaces. The rates are shown to be optimal in the minimax sense: they match with a lower bound of the minimax risk, which is also proved. Finally, we conduct a numerical study, over simulated data and over two real-data sets.
引用
收藏
页码:2990 / 3039
页数:50
相关论文
共 46 条
[1]   Estimation of functional regression models for functional responses by wavelet approximation [J].
Aguilera, Ana ;
Ocana, Francisco ;
Valderrama, Mariano .
FUNCTIONAL AND OPERATORIAL STATISTICS, 2008, :15-21
[2]   Electricity consumption prediction with functional linear regression using spline estimators [J].
Antoch, Jaromir ;
Prchal, Lubos ;
De Rosa, Maria Rosaria ;
Sarda, Pascal .
JOURNAL OF APPLIED STATISTICS, 2010, 37 (12) :2027-2041
[3]  
Ash RobertB., 1975, Topics in Stochastic Processes, V27
[4]   Model selection for regression on a fixed design [J].
Baraud, Y .
PROBABILITY THEORY AND RELATED FIELDS, 2000, 117 (04) :467-493
[5]  
BARAUD Y., 2002, ESAIM Probab. Stat., V6, P127
[6]   Estimator selection in the Gaussian setting [J].
Baraud, Yannick ;
Giraud, Christophe ;
Huet, Sylvie .
ANNALES DE L INSTITUT HENRI POINCARE-PROBABILITES ET STATISTIQUES, 2014, 50 (03) :1092-1119
[7]   Risk bounds for model selection via penalization [J].
Barron, A ;
Birgé, L ;
Massart, P .
PROBABILITY THEORY AND RELATED FIELDS, 1999, 113 (03) :301-413
[8]   Minimum contrast estimators on sieves: exponential bounds and rates of convergence [J].
Birge, L ;
Massart, P .
BERNOULLI, 1998, 4 (03) :329-375
[9]   Penalized contrast estimation in functional linear models with circular data [J].
Brunel, E. ;
Roche, A. .
STATISTICS, 2015, 49 (06) :1298-1321
[10]   Non-asymptotic adaptive prediction in functional linear models [J].
Brunel, Elodie ;
Mas, Andre ;
Roche, Angelina .
JOURNAL OF MULTIVARIATE ANALYSIS, 2016, 143 :208-232