Loading…

About the limits of raise regression to reduce condition number when three explanatory variables are involved

This manuscript shows that the raise regression can be considered as an appropriate methodology in order to reduce the approximate multicollinearity that naturally appears in problems of linear regression. When three explanatory variables are involved, its application reduces the condition number of...

Full description

Saved in:
Bibliographic Details
Published in:Rect@. Revista electrónica de comunicaciones y trabajos de ASEPUMA 2018, Vol.19 (1), p.45-62
Main Authors: Roldan, Antonio F., Salmeron, Roman, Garcia, Catalina
Format: Article
Language:English
Subjects:
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This manuscript shows that the raise regression can be considered as an appropriate methodology in order to reduce the approximate multicollinearity that naturally appears in problems of linear regression. When three explanatory variables are involved, its application reduces the condition number of the matrix associated to data set. Nevertheless, this procedure has a threshold: although the columns of X can be separated, it is proved that the condition number will never be less than a constant that can be easily worked out by using the elements of the initial matrix. Finally, the contribution is illustrated through an empirical example. Este trabajo muestra que la regresión alzada puede considerarse como una metodología apropiada para reducir la multicolinealidad aproximada que aparece de forma natural en los problemas de regresión lineal. Cuando se trata de tres variables explicativas, su aplicación reduce el número de condición de la matriz asociada al conjunto de datos. Sin embargo, este procedimiento tiene un umbral: aunque las columnas de dicha matriz se pueden separar, se demuestra que el número de condición nunca será menor que una constante que se puede obtener fácilmente utilizando los elementos de la matriz inicial. Finalmente, la contribución se ilustra a través de un ejemplo empírico.
ISSN:1575-605X
DOI:10.24309/recta.2018.19.1.04