Some Forecast Asymmetric GARCH Models for Distributions with Heavy Tails (original) (raw)

2020

Abstract

Crude oil prices are inuenced by a number of factors that are far beyond the traditionalsupply and demand dynamics such as West Texas Intermediate (WTI), Brent and Dubai. Thehigh frequency crude oil data exhibit non-constant variance. This paper models and forecaststhe exhibited uctuations via asymmetric GARCH models with the three commonly used errordistributions: Student'stdistribution, normal distribution and generalized error distribution(GED). The Maximum Likelihood Estimation (MLE) approach is used in the estimation ofthe asymmetric GARCH family models. The analysis shows that volatility estimates given bythe exponential generalized autoregressive conditional heteroskedasticity (EGARCH) modelexhibit generally lower forecast errors in returns of WTI oil spot price while the asymmetricpower autoregressive conditional heteroskedasticity (APARCH) model exhibits lower forecasterrors in returns of Brent oil spot price, therefore they are more accurate than the estimatesgiven b...

J. Onyeka-Ubaka hasn't uploaded this paper.

Create a free Academia account to let J. know you want this paper to be uploaded.

Ask for this paper to be uploaded.