A CUSUM type test for constant correlation that goes beyond a previously suggested correlation constancy test by considering Spearman's rho in arbitrary dimensions is proposed. Since the new test does not require the existence of any moments, the applicability on usually heavy-tailed financial data is greatly improved. The asymptotic null distribution is calculated using an invariance principle for the sequential empirical copula process. The limit distribution is free of nuisance parameters and critical values can be obtained without bootstrap techniques. A local power result and an analysis of the behavior of the test in small samples are provided.
|Number of pages||14|
|Journal||Computational Statistics & Data Analysis|
|Early online date||6 Apr 2013|
|Publication status||Published - Aug 2014|
- Multivariate sequential rank order process
- Structural break