Estimation of Value-at-Risk for Energy Commodities via CAViaR Model

摘要: This paper uses the Conditional Autoregressive Value at Risk model (CAViaR) proposed by Engle and Manganelli (2004) to evaluate value-at-risk for daily spot prices of Brent crude oil West Texas Intermediate covering period May 21th, 1987 Novermber 18th, 2008. Then accuracy estimates CAViaR model, Normal-GARCH, GED-GARCH was compared. The results show that all methods do good job low confidence level (95%), is best WTI price, Normal-GARCH Adaptive-CAViaR are price. However, high (99%), a WTI, four kind specifications well does badly result seems suggest as since directly quantile autoregression, but it not outperform although Normal-GARCH.