A Quadratic Classification Rule with Equicorrelated Training Vectors for Non Random Samples

作者：Leiva Ricardo; Roy Anuradha^*

来源：Communications in Statistics - Theory and Methods, 2011, 40(2): 213-231.

DOI：10.1080/03610920903427776

• Classification rules
• Multivariate equicorrelation
• Non random samples

This article proposes a quadratic extension of the traditional classification rules for multiple classes based on equicorrelated training vectors by using multivariate equicorrelation. This new classification rule can incorporate within sample dependencies, thus appropriate for non random samples.

• 出版日期2011