Independence test for high dimensional data based on regularized canonical correlation coefficients
Date of Issue2015
School of Physical and Mathematical Sciences
This paper proposes a new statistic to test independence between two high dimensional random vectors X:p1×1 and Y:p2×1. The proposed statistic is based on the sum of regularized sample canonical correlation coefficients of X and Y. The asymptotic distribution of the statistic under the null hypothesis is established as a corollary of general central limit theorems (CLT) for the linear statistics of classical and regularized sample canonical correlation coefficients when p1p1p1 and p2p2p2 are both comparable to the sample size nnn. As applications of the developed independence test, various types of dependent structures, such as factor models, ARCH models and a general uncorrelated but dependent case, etc., are investigated by simulations. As an empirical application, cross-sectional dependence of daily stock returns of companies between different sections in the New York Stock Exchange (NYSE) is detected by the proposed test.
The annals of statistics
© 2015 Institute of Mathematical Statistics. This paper was published in Annals of Statistics and is made available as an electronic reprint (preprint) with permission of Institute of Mathematical Statistics. The paper can be found at the following official DOI: [http://dx.doi.org/10.1214/14-AOS1284]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.