MODELLING THE VOLATILITY OF STOCK RETURNS IN SOME SELECTED AFRICAN COUNTRIES

This paper applied Multivariate Generalized Autoregressive Conditional Heteroscedasticity (MGARCH) Models to stock prices from three African countries. The parameter estimate of the VECH and BEKK forms provided a significant ARCH effects at (p<0.05) for RESID (-1)^2 for all the studied stock returns implying that volatility in the stock returns is influenced by the immediate past. In addition, the GARCH (-1) values are all significant at (p-value < 0.05) in VECH and BEKK, which means that volatility in the stock returns is caused by immediate past residuals. The dynamic conditional correlation (DCC) model was explored further by introducing the range in stock returns resulting in a model that incorporates high and low prices into the DCC framework. An empirical evaluation of this model on our three stocks was conducted, and the model performs excellently with the parameters’ p-value estimates significant. The results reviewed that the use of range data in the DCC model can improve the estimation of covariances of returns and increase the accuracy of covariance and VaR forecasts based on this model, compared with using closing prices only. The study showed that bad and good news increase volatility of stock return in different magnitudes which implies that the investment climate including the stability of microeconomic variables should be favorable to ensure growth in the Africa stock market. The DCC-RGARCH model was capable of utilizing all the characteristics and information concealed in the historical data. Researchers are urged to investigate its application more, particularly with regard to African stock prices.