(PHBS)

Publications

Home > Faculty & Research > Publications >

The Two-sided Weibull Distribution and Forecasting Financial Tail Risk

by Qian Chen, Richard H. Gerlach

ARTICLE | International Journal of Forecasting | Vol. 29, 2013


Abstract


A two-sided Weibull is developed for modelling the conditional financial return distribution, for the purpose of forecasting tail risk measures. For comparison, a range of conditional return distributions are combined with four volatility specifications in order to forecast the tail risk in seven daily financial return series, over a four-year forecast period that includes the recent global financial crisis. The two-sided Weibull performs at least as well as other distributions for Value at Risk (VaR) forecasting, but performs most favourably for conditional VaR forecasting, prior to the crisis as well as during and after it.

Keywords: Two-sided Weibull, Value-at-Risk, Expected shortfall, Back-testing, Global financial crisis, Volatility 
Popular Articles
Latest News
Campus Events