Free-knot spline smoothing for functional data

被引：24

作者：

Gervini, Daniel ^{[1
]}

机构：

[1] Univ Wisconsin, Dept Math Sci, Milwaukee, WI 53211 USA

来源：

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY | 2006年 / 68卷

关键词：

functional data analysis; Karhunen-Loeve decomposition; longitudinal data analysis; variance components;

D O I：

10.1111/j.1467-9868.2006.00561.x

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：

The paper introduces free-knot regression spline estimators for the mean and the variance components of a sample of curves. The asymptotic distribution of the mean estimator is derived, and asymptotic confidence bands are constructed. A comparative simulation study shows that free-knot splines estimate salient features of the functions (such as sharp peaks) more accurately than smoothing splines. This adaptive behaviour is also illustrated by an analysis of weather data.

引用

页码：671 / 687

页数：17

共 13 条

[1] SMOOTHING NOISY DATA WITH SPLINE FUNCTIONS [J].

WAHBA, G .

NUMERISCHE MATHEMATIK, 1975, 24 (05) :383-393

[2]

Friedman J., 2001, The elements of statistical learning, V1, DOI DOI 10.1007/978-0-387-21606-5

[3] Spline adaptation in extended linear models [J].

Hansen, MH ;

Kooperberg, C .

STATISTICAL SCIENCE, 2002, 17 (01) :2-20

[4] APPROXIMATION TO DATA BY SPLINES WITH FREE KNOTS [J].

JUPP, DLB .

SIAM JOURNAL ON NUMERICAL ANALYSIS, 1978, 15 (02) :328-343

[5] NONPARAMETRIC-ESTIMATION OF COMMON REGRESSORS FOR SIMILAR CURVE DATA [J].

KNEIP, A .

ANNALS OF STATISTICS, 1994, 22 (03) :1386-1427

[6] Free-knot polynomial splines with confidence intervals [J].

Mao, WX ;

Zhao, LH .

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2003, 65 :901-919

[7]

*MATLAB, 2005, MATLAB VERS 7 0 4

[8]

Ramsay J., 1997, FUNCTIONAL DATA ANAL, DOI DOI 10.1007/978-1-4757-7107-7

[9]

RICE JA, 1991, J ROY STAT SOC B MET, V53, P233

[10]

Schumaker L., 1980, SPLINE FUNCTIONS BAS

← 1 2 →