Ensemble Subsampling for Imbalanced Multivariate Two-Sample Tests

• Activity Number: 347
• Type: Topic Contributed
• Date/Time: Tuesday, August 6, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Business and Economic Statistics Section
• Author(s): Lisha Chen*+ and Wei Dou and Zhihua Qiao
• Companies: Yale University, Statistics Department and MIT and JPMorgan Chase
• Keywords: ensemble methods ; imbalanced learning ; nearest neighbors methods ; two-sample tests

Abstract

Some existing nonparametric two-sample tests for equality of multivariate distributions perform unsatisfactorily when the two sample sizes are imbalanced. In particular, the power of these tests tends to diminish with increasingly imbalanced sample sizes. In this paper, we propose a new testing procedure to solve this problem. The proposed test is based on a nearest neighbor method and employs a novel ensemble subsampling scheme to treat the imbalance of data. We demonstrate the strong power of the testing procedure by simulation study and real data example, and provide asymptotic analysis for our testing procedure.