A nonparametric test for a constant correlation matrix
Methodology
2014-10-29 v4
Abstract
We propose a nonparametric procedure to test for changes in correlation matrices at an unknown point in time. The new test requires only mild assumptions on the serial dependence structure and has considerable power in finite samples. We derive the asymptotic distribution under the null hypothesis of no change as well as local power results and apply the test to stock returns.
Cite
@article{arxiv.1210.1412,
title = {A nonparametric test for a constant correlation matrix},
author = {Dominik Wied},
journal= {arXiv preprint arXiv:1210.1412},
year = {2014}
}