Title: Comparison of EVT methods for GARCH-EVT approach applied to financial time series
Authors: Hibiki Kaibuchi - SOKENDAI The Graduate University of Advanced Studies (Japan) [presenting]
Yoshinori Kawasaki - The Institute of Statistical Mathematics (Japan)
Abstract: Managing extreme event risk in finance and insurance is vital in our modern society. It is known that the statistically justifiable modeling and prediction of rare events are challenging because the historical data on extreme events are inherently scarce. In order to prevent or prepare for unfavorable scenarios, the approaches based on extreme value theory (EVT) have been devised. The aim is to estimate conditional extreme quantiles (Value at Risk) using GARCH-EVT framework. For that, we: (i) pre-whiten the financial time series with a GARCH-type model for forecasting volatility; (ii) apply the semi-parametric bias-corrected tail estimators under $\beta$-mixing condition to the residuals from the GARCH analysis instead of the Peaks-Over-Thresholds (POT) method under IID condition. The results are illustrated on simulated data and on a financial real dataset.