CROSS-VALIDATORY CHOICE FOR THE NUMBER OF PRINCIPAL COMPONENTS IN PRINCIPAL COMPONENT REGRESSION

CROSS-VALIDATORY CHOICE FOR THE NUMBER OF PRINCIPAL COMPONENTS IN PRINCIPAL COMPONENT REGRESSION

We propose a cross-validatory method to choose the number of principal components in principal component regression based on the predicted error sum of squares. In the process of computation, we propose to use an approximation formula using a linear approximation based on the perturbation expansion....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the Japanese Society of Computational Statistics 1996, Vol.9(1), pp.53-59
Hauptverfasser: Shin, Jae-Kyoung, Tanaka, Yutaka
Format: Artikel
Sprache:eng
Schlagworte:
cross-validation
number of principal components
principal component regression
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose a cross-validatory method to choose the number of principal components in principal component regression based on the predicted error sum of squares. In the process of computation, we propose to use an approximation formula using a linear approximation based on the perturbation expansion. A numerical example is given to show the validity of the proposed method.
ISSN:0915-2350
1881-1337
DOI:10.5183/jjscs1988.9.53