Charles Explorer logo
🇬🇧

Testing the tail index in autoregressive models

Publication at Faculty of Mathematics and Physics |
2009

Abstract

We propose a class of nonparametric tests on the Pareto tail index of the innovation distribution in the linear autoregressive model. The simulation study illustrates a good performance of the tests.

Such tests have various applications in a study of flood flows, rainflow data, behavior of solids, atmospheric ozone layer and reliability analysis, in communication engineering, in stock markets and insurance.