Format

Send to

Choose Destination
Biometrics. 2009 Dec;65(4):1021-9. doi: 10.1111/j.1541-0420.2009.01200.x.

Shrinkage-based diagonal discriminant analysis and its applications in high-dimensional data.

Author information

1
Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, North Carolina 27705, USA. herbert.pang@duke.edu

Abstract

High-dimensional data such as microarrays have brought us new statistical challenges. For example, using a large number of genes to classify samples based on a small number of microarrays remains a difficult problem. Diagonal discriminant analysis, support vector machines, and k-nearest neighbor have been suggested as among the best methods for small sample size situations, but none was found to be superior to others. In this article, we propose an improved diagonal discriminant approach through shrinkage and regularization of the variances. The performance of our new approach along with the existing methods is studied through simulations and applications to real data. These studies show that the proposed shrinkage-based and regularization diagonal discriminant methods have lower misclassification rates than existing methods in many cases.

PMID:
19302409
PMCID:
PMC2794982
DOI:
10.1111/j.1541-0420.2009.01200.x
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Wiley Icon for PubMed Central
Loading ...
Support Center