Document Type

Lecture

Publication Date

3-26-2026

Abstract

Principal component analysis (PCA) is a statistical technique for the dimensionality reduction of data, minimizing information loss and increasing interpretability. It does so by first extracting new uncorrelated variables which successively maximize variance in the remaining data spaces and then cutting off principal components (PCs) corresponding to small singular values.

However, for various applications, certain PCs must be eliminated to enhance the stability and reliability, although the corresponding singular values are not small. This article introduces an innovative statistical criterion for the selection of reliable PCs, called the α-Test.

The proposed test is analyzed, and effective computational algorithms are discussed for an automatic picking of reliable PCs. The effectiveness of the α-Test is verified with numerous synthetic systems in regression analysis and also with real datasets.

Relational Format

presentation

Accessibility Status

Searchable text

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.