A Direct Estimation Approach to Sparse Linear Discriminant Analysis

• 成果类型: Article
• 署名作者: Cai, Tony; Liu, Weidong
• 署名单位: University of Pennsylvania; Shanghai Jiao Tong University; Shanghai Jiao Tong University
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1198/jasa.2011.tm11199
• 发表日期: 2011
• 页码: 1566-1577
• 关键词: Classification; cancer

摘要

This article considers sparse linear discriminant analysis of high-dimensional data. In contrast to the existing methods which are based on separate estimation of the precision matrix Omega and the difference delta of the mean vectors, we introduce a simple and effective classifier by estimating the product Omega delta directly through constrained l(1) minimization. The estimator can be implemented efficiently using linear programming and the resulting classifier is called the linear programming discriminant (LPD) rule. The LPD rule is shown to have desirable theoretical and numerical properties. It exploits the approximate sparsity of Omega delta and as a consequence allows cases where it can still perform well even when Omega and/or delta cannot be estimated consistently. Asymptotic properties of the LPD rule are investigated and consistency and rate of convergence results are given. The LPD classifier has superior finite sample performance and significant computational advantages over the existing methods that require separate estimation of Omega and delta. The LPD rule is also applied to analyze real datasets from lung cancer and leukemia studies. The classifier performs favorably in comparison to existing methods.