GARCH models in forecasting the volatility of the world’s oil prices

Abstract

© 2018, Springer International Publishing AG. This study was conducted to forecast the volatility of the world’s oil prices. Using the daily data of the WTI spot oil price collected from the US Energy Information Administration in the period from 01/02/1986 to 25/4/2016, estimation using models such as GARCH(1,1), EGARCH(1,1), GJR-GARCH(1,1) was made under 4 different distributions: normal distribution, Student’s t-distribution, generalized error distribution (GED), skewed Student’s t-distribution. The results show that the EGARCH(1,1) model with Student’s t-distribution provides the most accurate forecast. In addition, it is also shown that the volatility of crude oil price in the future can be predicted by the past volatility while crude oil price shock has a relatively small impact on oil price volatility.