Abstract
This study looks at the performance of volatility models in forecasting share returns of the Industrial sector on the JSE. The major goal of the study is to determine which volatility model produces better forecast results of share returns and also to see which volatility model performs better between a symmetric model and an asymmetric model. In general, share return forecasting presents significant implications for market participants especially those whose major focus is on risk-adjusted returns. Having the ability to forecast tomorrow’s share return accurately provides an edge for market participants in making sound investment decisions. However, achieving a precise prediction in volatile markets such as stock markets is a challenging issue. Share prices are random variables and this feature makes it difficult to predict their returns accurately. Currently, the GARCH models are the most popular volatility models for forecasting share returns and have been used extensively by researchers in developed countries though there has been a lack of consensus as to which volatility model produces better forecast results. In this study, four volatility models were used and these include: ARMA (1,1), GARCH (1,1), T-GARCH (0,2) and an E-GARCH (2,2) model. From these four models, an ARMA (1,1) model was used as a benchmark model against the other three models. The major reason why these four models were selected for the study is that the best forecast results have come from either one of the four models. Two types of sample forecast namely In-sample and out-of-sample forecast were conducted to determine which volatility model produced better forecast results. The results of the study indicate that an ARMA (1,1) benchmark model outperformed all the other three family of GARCH models in a pseudo out-of sample forecast. On the other hand, a GARCH (1,1) model performed slightly better than the EGARCH (2,2) and TGARCH (0,2) models. These results are aligned with some of the studies in South Africa and abroad.
M.Com. (Finance)