Using mutual information to measure the predictive power of principal components

Artemiou, Andreas ORCID: https://orcid.org/0000-0002-7501-4090 2021. Using mutual information to measure the predictive power of principal components. Li, Bing and Bura, Efstathia, eds. Festschrift to Dennis Cook, Springer,

Full text not available from this repository.

Abstract

In this work we propose the use of mutual information to measure the predictive potential of principal components in regression. We show that this criterion produces the same results as previous works which used the correlation to measure the strength of the relationship between the response variable with the extracted principal components in Gaussian settings. We demonstrate this in the linear regression model and also beyond that, in the conditional mean model and the conditional independence model, two common choices in sufficient dimension reduction, achieving a connection between unsupervised and supervised dimension reduction methods.

Item Type:	Book Section
Status:	In Press
Schools:	Schools > Mathematics
Subjects:	Q Science > QA Mathematics
Publisher:	Springer
Last Modified:	09 Nov 2022 09:44
URI:	https://orca.cardiff.ac.uk/id/eprint/136830

Actions (repository staff only)

Edit Item