The principal problem with principal components regression

被引：27

作者：

Artigue, Heidi ^{[1
]}

Smith, Gary ^{[1
]}

机构：

[1] Pomona Coll, Dept Econ, 425 N Coll Ave, Claremont, CA 91711 USA

来源：

COGENT MATHEMATICS & STATISTICS | 2019年 / 6卷

关键词：

principal components regression; PCA; factor analysis; Big Data; data reduction; VARIABLES; MODELS; NUMBER;

D O I：

10.1080/25742558.2019.1622190

中图分类号：

O1 [数学];

学科分类号：

0701 ; 070101 ;

摘要：

Principal components regression (PCR) reduces a large number of explanatory variables in a regression model down to a small number of principal components. PCR is thought to be more useful, the more numerous the potential explanatory variables. The reality is that a large number of candidate explanatory variables does not make PCR more valuable; instead, it magnifies the failings of PCR.

引用

页数：11

共 34 条

[1]

Alibuhtto M. C., 2015, P 5 INT S 2015 S E U

[2]

Athey S, 2018, The economics of artificial intelligence: An agenda, P507

[3] A nonlinear principal component analysis to study archeometric data [J].

Bitetto, Alessandro ;

Mangone, Annarosa ;

Mininni, Rosa Maria ;

Giannossa, Lorena C. .

JOURNAL OF CHEMOMETRICS, 2016, 30 (07) :405-415

[4] Quantifying Infinite-Dimensional Data: Functional Data Analysis in Action [J].

Chen K. ;

Zhang X. ;

Petersen A. ;

Müller H.-G. .

Statistics in Biosciences, 2017, 9 (2) :582-604

[5] THE USE OF PRINCIPAL COMPONENTS IN THE ANALYSIS OF NEAR-INFRARED SPECTRA [J].

COWE, IA ;

MCNICOL, JW .

APPLIED SPECTROSCOPY, 1985, 39 (02) :257-266

[6] Modified kernel principal component analysis based on local structure analysis and its application to nonlinear process fault diagnosis [J].

Deng, Xiaogang ;

Tian, Xuemin ;

Chen, Sheng .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2013, 127 :195-209

[7] On the number of principal components: A test of dimensionality based on measurements of similarity between matrices [J].

Dray, Stephane .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 52 (04) :2228-2237

[8] The raise method. An alternative procedure to estimate the parameters in presence of collinearity [J].

Garcia Garcia, Catalina ;

Garcia Perez, Jose ;

Soto Liria, Jose .

QUALITY & QUANTITY, 2011, 45 (02) :403-423

[9] BIG DATA AND DATA SCIENCE METHODS FOR MANAGEMENT RESEARCH [J].

George, Gerard ;

Osinga, Ernst C. ;

Lavie, Dovev ;

Scott, Brent A. .

ACADEMY OF MANAGEMENT JOURNAL, 2016, 59 (05) :1493-1507

[10] Searching for the core variables in principal components analysis [J].

Gimenez, Yanina ;

Giussani, Guido .

BRAZILIAN JOURNAL OF PROBABILITY AND STATISTICS, 2018, 32 (04) :730-754

← 1 2 3 4 →