Abstract
We analyze the extreme value dependence of independent, not necessarily identically distributed multivariate regularly varying random vectors. More specifically, we propose estimators of the spectral measure locally at some time point and of the spectral measures integrated over time. The uniform asymptotic normality of these estimators is proved under suitable nonparametric smoothness and regularity assumptions. We then use the process convergence of the integrated spectral measure to devise consistent tests for the null hypothesis that the spectral measure does not change over time.
Acknowledgment
I would like to thank Laurens de Haan for helpful discussions in an early stage of this project. Remarks by anonymous referees have led to an improved presentation of our ideas and results.
Citation
Holger Drees. "Statistical inference on a changing extreme value dependence structure." Ann. Statist. 51 (4) 1824 - 1849, August 2023. https://doi.org/10.1214/23-AOS2314
Information