B0159
Title: Statistics for heteroscedastic time series extremes
Authors: Axel Buecher - Ruhr-University Bochum (Germany) [presenting]
Tobias Jennessen - Heinrich Heine University Duesseldorf (Germany)
Abstract: A study recently introduced a stochastic model that allows for heteroscedasticity of extremes. The model is extended to the situation where the observations are serially dependent, which is crucial for many practical applications. Statistical inference for the integrated skedasis function is considered, with a particular emphasis on testing the null hypothesis of homoscedastic extremes. Unlike in the serially independent case, limiting distributions under the null hypothesis are not pivotal. To circumvent this, two tests are proposed based on an appropriate multiplier bootstrap scheme and self-normalization, respectively.
