A0234
Title: Tail risk forecasting of realized volatility CAViaR models
Authors: Cathy W-S Chen - Feng Chia University (Taiwan) [presenting]
Hsiao-Yun Hsu - Feng Chia University (Taiwan)
Toshiaki Watanabe - Hitotsubashi University (Japan)
Abstract: A new class of RES-CAViaR (conditional autoregressive value-at-risk) models that incorporate daily realized volatility and expected shortfall (ES) is proposed to forecast VaR and ES simultaneously. Weekly and monthly realized volatilities in the proposed model are further considered to approximate a long-memory process. The Bayesian adaptive Markov chain Monte Carlo approach is employed to estimate all unknown parameters and to jointly predict daily VaR and ES over a 4-year out-of-sample period, including the COVID-19 pandemic. The results show that the realized CAViaR-type models outperform in terms of three backtests, four loss-function criteria, and ES measurement at the 1\% level.
