A perfect smoother

被引:1025
作者
Eilers, PHC [1 ]
机构
[1] Leiden Univ, Ctr Med, Dept Med Stat, NL-2300 RC Leiden, Netherlands
关键词
Codes (symbols) - Least squares approximations;
D O I
10.1021/ac034173t
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The well-known and popular Savitzky-Golay filter has several disadvantages. A very attractive alternative is a smoother based on penalized least squares, extending ideas presented by Whittaker 80 years ago. This smoother is extremely fast, gives continuous control over smoothness, interpolates automatically, and allows fast leave-one-out cross-validation. It can be programmed in a few lines of Matlab code. Theory, implementation, and applications are presented.
引用
收藏
页码:3631 / 3636
页数:6
相关论文
共 11 条
[1]   Flexible smoothing with B-splines and penalties [J].
Eilers, PHC ;
Marx, BD .
STATISTICAL SCIENCE, 1996, 11 (02) :89-102
[2]  
EILERS PHC, 1994, GRAPHIC GEMS, V4, P241
[3]  
Fan J., 1996, LOCAL POLYNOMICAL MO
[4]  
Hastie T., 1990, GEN ADDITIVE MODELS
[5]   Postwar US business cycles: An empirical investigation [J].
Hodrick, RJ ;
Prescott, EC .
JOURNAL OF MONEY CREDIT AND BANKING, 1997, 29 (01) :1-16
[6]  
Loader C., 1999, LOCAL REGRESSION LIK, DOI DOI 10.1007/B98858
[7]  
Pandit S. M., 1983, Time Series and System Analysis With Applications
[8]  
Percival D., 2000, CA ST PR MA
[9]  
Press W.H., 1992, NUMERICAL RECIPES C
[10]   SMOOTHING + DIFFERENTIATION OF DATA BY SIMPLIFIED LEAST SQUARES PROCEDURES [J].
SAVITZKY, A ;
GOLAY, MJE .
ANALYTICAL CHEMISTRY, 1964, 36 (08) :1627-&