Influence properties of partial least squares regression

被引：19

作者：

Serneels, S

Croux, C

Van Espen, PJ ^{[1
]}

机构：

[1] Univ Antwerp, Dept Chem, B-2020 Antwerp, Belgium

[2] Katholieke Univ Leuven, Dept Appl Econ, Louvain, Belgium

来源：

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS | 2004年 / 71卷 / 01期

关键词：

partial least squares regression; influence function; variance estimation; diagnostic plot;

D O I：

10.1016/j.chemolab.2003.10.009

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we compute the influence function (IF) for partial least squares (PLS) regression. Thereunto, we design two alternative algorithms, according to the PLS algorithm used. One algorithm for the computation of the influence function is based on the Helland PLS algorithm. whilst the other is compatible with SIMPLS. The calculation of the influence function leads to new influence diagnostic plots for PLS. An alternative to the well-known Cook's Distance (CD) plot is proposed. as well as a variant which is sample specific. Moreover, a novel estimate of prediction variance is deduced. The validity of the latter is corroborated by dint of a Monte Carlo simulation. (C) 2004 Elsevier B.V. All rights reserved.

引用

页码：13 / 20

页数：8

共 26 条

[1]

[Anonymous], 1966, Multivariate Analysis

[2] Latent variable multivariate regression modeling [J].