Disentangled oil shocks and stock market volatility in Nigeria and South Africa : a GARCH-MIDAS approach

Abstract

In this study, we investigate the effects of disentangled oil shocks on the volatility of the stock markets of Nigeria and South Africa using the Mixed Data Sampling variant of the Generalized Autoregressive Conditional Heteroscedasticity (GARCH-MIDAS) model. The disentangled oil shocks involve oil supply shock, economic activity shock, oil consumption demand shock, and oil inventory demand shock covering January 2010 and July 2022. Overall, we find that the stock market volatilities of Nigeria and South Africa respond similarly to oil supply shock and oil consumption demand shock but differently to economic activity shock and oil inventory demand shock. The unusual increase in the volatility of Nigeria’s stock market has been attributed to the loss of investors’ confidence which takes a too long time to be restored. Our results are robust to alternative forecast sampling techniques, particularly fixed and rolling windows.