A generalized view on continuum regression

被引:27
作者
Björkström, A [1 ]
Sundberg, R [1 ]
机构
[1] Univ Stockholm, S-10691 Stockholm, Sweden
关键词
cross-validation; linear prediction; near collinearity; partial least squares regression (PLS); principal component regression (PCR); ridge regression; shrinkage;
D O I
10.1111/1467-9469.00134
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 generalize the relationship between continuum regression (Stone & Brooks, 1990) and ridge regression, by showing that any optimization principle will yield a regressor proportional to a ridge regressor, provided only that the principle implies maximizing a function of the regressor's sample correlation coefficient and its sample variance, This relationship shows that continuum regression as defined via ridge regression ("least squares ridge regression") is a more generally valid methodology than previously realized, and also opens up for alternative choices of its second and subsequent factors.
引用
收藏
页码:17 / 30
页数:14
相关论文
共 14 条
[1]  
Bjorkstrom A, 1996, J ROY STAT SOC B MET, V58, P703
[2]  
Brown P. J., 1993, MEASUREMENT REGRESSI
[3]   PLS SHRINKS [J].
DEJONG, S .
JOURNAL OF CHEMOMETRICS, 1995, 9 (04) :323-326
[4]   EXTENDING THE RELATIONSHIP BETWEEN RIDGE-REGRESSION AND CONTINUUM REGRESSION [J].
DEJONG, S ;
FAREBROTHER, RW .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1994, 25 (02) :179-181
[5]  
DEJONG S, 1993, J CHEMOMETR, V7, P551
[6]  
FEARN T, 1983, J R STAT SOC C-APPL, V32, P73
[7]   A STATISTICAL VIEW OF SOME CHEMOMETRICS REGRESSION TOOLS [J].
FRANK, IE ;
FRIEDMAN, JH .
TECHNOMETRICS, 1993, 35 (02) :109-135
[8]  
Goutis C, 1996, ANN STAT, V24, P816
[9]   POWER GENERALIZATION OF RIDGE REGRESSION [J].
HOERL, AE ;
KENNARD, RW .
TECHNOMETRICS, 1975, 17 (02) :269-269
[10]  
HOERL AE, 1985, APPL STAT-J ROY ST C, V34, P114