DNA microarray technologies, which monitor simultaneously, the expression pattern of thousands of individual genes in different biological systems have resulted in a tremendous increase of the amount of available gene expression data and have provided new insights into gene expression during development, within disease processes, and across species. However, microarray gene expression data are characterized by very high dimensionality (genes), relatively small numbers of samples (observations), irrelevant features, as well as collinear and multivariate characteristics. These features complicate the interpretation and analysis of microarray data, and the complexity of such data means that its analysis entails a high computational cost. This situation motivated the researchers to develop a new method for analyzing microarray data. In this paper, we propose a simple gene selection and multivariate fuzzy statistical analysis methods. The proposed method was applied to microarray data from leukemia patients; specifically, it was used to interpret the gene expression pattern and analyze the leukemia subtype whose expression profiles correlated with four cases of acute leukemia gene expression. © 2005 Elsevier Ltd. All rights reserved.