Model selection for future data in the case of multivariate regression analysis

The problem of variable selection in multivariate regression analysis is considered. The method of predictive sample reuse derived by Geisser and Eddy is extended to the multivariate linear regression case. By applying this method to real data it is compared with McKay's ""adequate su...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:South African statistical journal 1983-01, Vol.17 (2), p.147-164
1. Verfasser: Van der Merwe, A.J., Groenewald, P.C.N., D e WaaL, D.J. and Van der Merwe, C.A.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The problem of variable selection in multivariate regression analysis is considered. The method of predictive sample reuse derived by Geisser and Eddy is extended to the multivariate linear regression case. By applying this method to real data it is compared with McKay's ""adequate subsets"" procedure, Mallows' Cp statistic and Allen's PRESS.
ISSN:0038-271X