The Sensitivity of A Test Based on Spearman's Rho in Cross-Correlation Change Point Problems
Abstract
In change point problems, there are three main questions that researchers are interested in. First of all, is there a change point or not? Second, when does the change point occur in a time series? Third, how quickly can we detect the change point? In this thesis, we first explain what a change point is, and what a cross-correlation is. We then discuss prior research in this area. Then we discuss and examine a test based on Spearman's rho, introduced by Wied and Dehling (2011), which tests the null hypothesis of no change point, and compare the change point we set with the results from the proposed statistic in simulation. We also use this statistic on data we selected from the U.S. stock market. We conclude with the pros and cons of this statistical method, and how we can detect the change point sensitively using the proposed statistic.
