Robust estimators of high order derivatives of regression functions

被引：21

作者：

Boente, G ^{[1
]}

Rodriguez, D

机构：

[1] Univ Buenos Aires, RA-1053 Buenos Aires, DF, Argentina

[2] Consejo Nacl Invest Cient & Tecn, RA-1033 Buenos Aires, DF, Argentina

来源：

STATISTICS & PROBABILITY LETTERS | 2006年 / 76卷 / 13期

关键词：

robust estimation; smoothing techniques; bandwidth selectors; kernel weights; asymptotic properties;

D O I：

10.1016/j.spl.2006.01.011

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：

We consider robust estimates for the derivatives of order v of the regression function. Uniform consistency, allowing to construct a robust data-driven bandwidth, and asymptotically normality results are established. The asymptotic efficiency of the proposed estimates is that of the related M-estimators. (C) 2006 Elsevier B.V. All rights reserved.

引用

页码：1335 / 1344

页数：10

共 17 条

[1] Robust plug-in bandwidth estimators in nonparametric regression [J].

Boente, G ;

Fraiman, R ;

Meloche, J .

JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1997, 57 (01) :109-142

[2]

BOENTE G, 2005, ROBUST ESTIMATORS HI

[3] Resistant selection of the smoothing parameter for smoothing splines [J].

Cantoni, E ;

Ronchetti, E .

STATISTICS AND COMPUTING, 2001, 11 (02) :141-146

[4] NONPARAMETRIC REGRESSION-ANALYSIS OF GROWTH-CURVES [J].

GASSER, T ;

MULLER, HG ;

KOHLER, W ;

MOLINARI, L ;

PRADER, A .

ANNALS OF STATISTICS, 1984, 12 (01) :210-229

[5]

GASSER T, 1985, J ROY STAT SOC B MET, V47, P238

[6] A FLEXIBLE AND FAST METHOD FOR AUTOMATIC SMOOTHING [J].

GASSER, T ;

KNEIP, A ;

KOHLER, W .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1991, 86 (415) :643-652

[7]

GASSER T, 1984, SCAND J STAT, V11, P171

[8]

HALL DT, 1990, ORGAN DYN, V18, P4

[9] UNIFORM CONSISTENCY OF A CLASS OF REGRESSION FUNCTION ESTIMATORS [J].

HARDLE, W ;

LUCKHAUS, S .

ANNALS OF STATISTICS, 1984, 12 (02) :612-623

[10]

HARDLE W, 1985, SCAND J STAT, V12, P233

← 1 2 →