 |
 |
|
|
| HAL: hal-00134226, version 1 |
| arXiv: math.ST/0703056 |
| Detailed view |  Export this paper |
 |
| Journal of Nonparametric Statistics 17 (2005) 841-856 |
|
|
|
|
| Quantile regression when the covariates are functions |
|
|
Hervé Cardot 1Christophe Crambes 2 |
|
|
| (2005-10) |
|
|
|
| This paper deals with a linear model of regression on quantiles when the explanatory variable takes values in some functional space and the response is scalar. We propose a spline estimator of the functional coefficient that minimizes a penalized L1 type criterion. Then, we study the asymptotic behavior of this estimator. The penalization is of primary importance to get existence and convergence. |
|
|
|
|
|
|
|
|
|
|
|
| 1: | Centre d'Economie et Sociologie appliquées à l'Agriculture et aux Espaces Ruraux (CESAER) |
|
|
|
Institut national de la recherche agronomique (INRA) |
|
|
| 2: | Laboratoire de Statistiques et Probabilités (LSProba) |
|
|
|
CNRS : UMR5583 – Université Paul Sabatier [UPS] - Toulouse III – Institut National des Sciences Appliquées (INSA) - Toulouse |
|
|
|
|
|
|
|
|
|
| Subject | : | Mathematics/Statistics |
|
|
| analyse de données fonctionnelles – quantiles conditionnels – fonctions splines – pénalisation |
|
|
|
| Attached file list to this document: | ||||||||||
|
||||||||||
|
|
|
| hal-00134226, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00134226 | |
| oai:hal.archives-ouvertes.fr:hal-00134226 | |
| From: Christophe Crambes | |
| Submitted on: Friday, 2 March 2007 10:11:08 | |
| Updated on: Friday, 2 March 2007 10:16:54 | |
