CMStatistics 2017: Start Registration
View Submission - CMStatistics
Title: Identification of a structural break in the serial dependence of a time series of extremes Authors:  Debbie Dupuis - HEC Montreal (Canada) [presenting]
Luca Trapin - University of Bologna (Italy)
Abstract: The analysis of extreme values in a stationary time series requires careful consideration of any dependence appearing in the extremes of the series. Thus, it is important to detect any changes in the temporal dependence of extreme values. We work within a hierarchical trawl-based framework to establish the first test for a change-point in the extremal dependence of a stationary time series. The test is flexible, easy to use, and can be extended along several lines. The asymptotic distributions of our estimators and our test statistics are established. A large simulation study verifies the good finite sample properties. We apply the test to surface level ozone data and show that there has been an increase in the serial dependence of their extreme levels in recent years.