A Quadratic Classifier for High-Dimension, Low-Sample-Size Data Under the Strongly Spiked Eigenvalue Model

Abstract

We consider a classifier for high-dimensional data under the strongly spiked eigenvalue (SSE) model. We create a new classification procedure on the basis of the high-dimensional eigenstructure. We propose a quadratic classification procedure by using a data transformation. We also prove that our proposed classification procedure has a consistency property for misclassification rates. We discuss performances of our classification procedure in simulations and real data analyses using microarray data sets.