Performance of Generalized Autoregressive Conditional Heteroscedasticity (GARCH) Models in Modeling Volatility of Brent Crude Oil Price
Keywords:
Akaike Information Criteria (AIC), Autoregressive Conditional Heteroskedasticity (ARCH), Autoregressive Conditional Heteroskedasticity Langrange Multiplier (ARCH LM), Hannan-Quinn Information Criteria (HQIC), Schwarz Information Criteria (SIC), VolatilityAbstract
Fluctuations in the price of crude oil determines the economic state of many nations especially the oil producing ones, it becomes important to examine these fluctuations, hence the GARCH models were applied to model the volatility in the price of brent crude oil to determine the best model suitable for predicting future volatility. Descriptive statistics of the stock price and its returns were obtained, some inferential tests were employed to examine the stationarity and the goodness of fit of the daily price and the return under different distributions – the Gaussian, the Student t and the Generalized Error Distributions. Results showed that the price of crude oil dropped between 2014 and 2016 and drastically dropped in 2020. Among the competing models, Exponential GARCH(1,1) with Student t distribution was the best model with the least values of AIC, SBIC and HQIC respectively. The result showed negative significant value in the coefficient of its asymmetric parameter, suggesting that bad news or vital event such as COVID19 has larger effect on the volatility in the price of the Brent crude oil. This study therefore recommended the use of Exponential GARCH model in modelling or predicting volatility in the stock price of crude oils.
