Journal of the Korean Data and Information Science Society
- Volume 8 Issue 2
- /
- Pages.127-134
- /
- 1997
- /
- 1598-9402(pISSN)
Numerical Investigations in Choosing the Number of Principal Components in Principal Component Regression - CASE I
- Shin, Jae-Kyoung (Dept. of Statistics, Changwon National University) ;
- Moon, Sung-Ho (Dept. of Statistics, Pusan University of Foreign Studies)
- Published : 1997.10.30
Abstract
A method is proposed for the choice of the number of principal components in principal component regression based on the predicted error sum of squares. To do this, we approximately evaluate that statistic using a linear approximation based on the perturbation expansion. In this paper, we apply the proposed method to various data sets and discuss some properties in choosing the number of principal components in principal component regression.
Keywords
- Principal component regression;
- Influence function;
- Predicted error sum of squares(PRESS);
- Cross-validatory method