Regularized linear discriminant analysis and its application in microarrays

TLDR

SCRDA builds on the nearest shrunken centroids approach to address high‑dimensional classification. The paper introduces SCRDA, a modified linear discriminant analysis called shrunken centroids regularized discriminant analysis. SCRDA is tailored for high‑dimensional, low‑sample‑size classification, such as microarray data, and supports feature elimination for gene selection. SCRDA achieves strong classification performance, outperforming PAM and rivaling SVMs, and is available as the open‑source R package “rda” on CRAN.

Abstract

In this paper, we introduce a modified version of linear discriminant analysis, called the "shrunken centroids regularized discriminant analysis" (SCRDA). This method generalizes the idea of the "nearest shrunken centroids" (NSC) (Tibshirani and others, 2003) into the classical discriminant analysis. The SCRDA method is specially designed for classification problems in high dimension low sample size situations, for example, microarray data. Through both simulated data and real life data, it is shown that this method performs very well in multivariate classification problems, often outperforms the PAM method (using the NSC algorithm) and can be as competitive as the support vector machines classifiers. It is also suitable for feature elimination purpose and can be used as gene selection method. The open source R package for this method (named "rda") is available on CRAN (http://www.r-project.org) for download and testing.