A Nonparametric Test for a Constant Correlation Matrix
Forthcoming in Econometric Reviews
29 Pages Posted: 19 Jan 2014 Last revised: 30 Oct 2014
Date Written: October 29, 2014
We propose a nonparametric procedure to test for changes in correlation matrices at an unknown point in time. The new test requires constant expectations and variances, but 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.
Keywords: Fluctuation test; Functional delta method; Gaussian process; Local power
JEL Classification: C12, C14, C32, C58
Suggested Citation: Suggested Citation