A Variable Selection Criterion for Two Sets of Principal Component Scores in Principal Canonical Correlation Analysis |
| |
| Authors: | Toru Ogura Yasunori Fujikoshi Takakazu Sugiyama |
| |
| Affiliation: | 1. Department of Industrial and Systems Engineering , Chuo University , Tokyo , Japan ogura@indsys.chuo-u.ac.jp;3. Department of Mathematics , Hiroshima University , Higashi-Hiroshima , Japan;4. Faculty of Technology , Soka University , Tokyo , Japan |
| |
| Abstract: | Canonical correlation analysis (CCA) is often used to analyze the correlation between two random vectors. However, sometimes interpretation of CCA results may be hard. In an attempt to address these difficulties, principal canonical correlation analysis (PCCA) was proposed. PCCA is CCA between two sets of principal component (PC) scores. We consider the problem of selecting useful PC scores in CCA. A variable selection criterion for one set of PC scores has been proposed by Ogura (2010), here, we propose a variable selection criterion for two sets of PC scores in PCCA. Furthermore, we demonstrate the effectiveness of this criterion. |
| |
| Keywords: | Canonical correlation analysis Principal component analysis Variable selection |
|
|
