Quantile regression when the covariates are functions

被引：102

作者：

Cardot, H ^{[1
]}

Crambes, C

Sarda, P

机构：

[1] INRA Toulouse, F-31326 Castanet Tolosan, France

[2] Univ Toulouse 3, Lab Stat & Probabil, UMR C5583, F-31062 Toulouse, France

[3] Univ Toulouse le Mirail, GRIMM, EA 3686, F-31058 Toulouse, France

来源：

JOURNAL OF NONPARAMETRIC STATISTICS | 2005年 / 17卷 / 07期

关键词：

functional data analysis; conditional quantiles; B-spline functions; roughness penalty;

D O I：

10.1080/10485250500303015

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：

This article 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 L-1 type criterion. Then, we study the asymptotic behavior of this estimator. The penalization is of primary importance to get existence and convergence.

引用

页码：841 / 856

页数：16

共 27 条

[1]

[Anonymous], 1997, SPRINGER SERIES STAT

[2] ASYMPTOTIC THEORY OF LEAST ABSOLUTE ERROR REGRESSION [J].