Smoothing splines estimators in functional linear regression with errors-in-variables

被引:47
|
作者
Cardot, Herve
Crambes, Christophe
Kneip, Alois
Sarda, Pascal
机构
[1] Univ Toulouse 3, UMR C5583, Lab Stat & Probabil, F-31062 Toulouse, France
[2] INRA Dijon, CESAER, ENESAD, F-21079 Dijon, France
[3] Univ Bonn, Dept Econ, Stat Abt, D-53113 Bonn, Germany
关键词
functional linear model; smoothing splines; penalization; errors-in-variables; total least squares;
D O I
10.1016/j.csda.2006.07.029
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The total least squares method is generalized in the context of the functional linear model. A smoothing splines estimator of the functional coefficient of the model is first proposed without noise in the covariates and an asymptotic result for this estimator is obtained. Then, this estimator is adapted to the case where the covariates are noisy and an upper bound for the convergence speed is also derived. The estimation procedure is evaluated by means of simulations. (c) 2006 Elsevier B.V. All rights reserved.
引用
下载
收藏
页码:4832 / 4848
页数:17
相关论文
共 50 条