Modeling rare events through a pRARMAX process |
| |
Authors: | Marta Ferreira,Luí sa Canto e Castro |
| |
Affiliation: | 1. Department of Mathematics and Center of Mathematics, University of Minho, Portugal;2. Faculty of Sciences and Center of Statistics, University of Lisbon, Portugal |
| |
Abstract: | 7 and 8 introduce a power max-autoregressive process, in short pARMAX, as an alternative to heavy tailed ARMA when modeling rare events. In this paper, an extension of pARMAX is considered, by including a random component which makes the model more applicable to real data. We will see conditions under which this new model, here denoted as pRARMAX, has unique stationary distribution and we analyze its extremal behavior. Based on Bortot and Tawn (1998), we derive a threshold-dependent extremal index which is a functional of the coefficient of tail dependence of 14 and 15 which in turn relates with the pRARMAX parameter. In order to fit a pRARMAX model to an observed data series, we present a methodology based on minimizing the Bayes risk in classification theory and analyze this procedure through a simulation study. We illustrate with an application to financial data. |
| |
Keywords: | Extreme value theory Max-autoregressive models Classification theory Bayes error |
本文献已被 ScienceDirect 等数据库收录! |
|