CMStatistics 2018: Start Registration
View Submission - CFE
Title: Value at risk and extreme value theory for oil prices: a long memory multivariate GARCH approach Authors:  Malvina Marchese - Cass Business School (United Kingdom)
Francesca Di Iorio - University of Naples Federico II (Italy)
Malvina Marchese - Cass Business School (United Kingdom) [presenting]
Abstract: The purpose is to examine the performance of several short and long memory multivariate volatility models for the crude oil spot and futures returns of three major oil markets, namely Brent WTI and Dubai, to estimate value and risk and the expected shortfalls for long and short positions. The results show that long memory multivariate GARCH models with asymmetries significantly over perform their short memory counterparts from a risk management perspective. Optimal portfolio weights and optimal hedge ratios are calculated with the fractionally integrated DCC model in order to suggest a crude oil hedge strategy. The empirical findings suggest holding crude oil futures to spot for Brent and Dubai and oil spot to futures for WTI. Finally, we show that the fractionally integrated DCC model is most effective in term of reducing the variance of the portfolio.