Abstract:
This study sought to model the stock market return volatility at the Nairobi Securities Exchange (NSE)
in the presence of structural breaks. Using daily NSE 20 share index for the period
04/01/2010 to 29/12/2017, the market return volatility was modeled using different GARCH type
models and taking into account four endogenously identified structural breaks. The market exhibited a
non-normal distribution that was leptokurtic and negatively skewed and also showed evidence for
ARCH effects, volatility clustering, and volatility persistence. We found that by considering structural
breaks, volatility persistence was reduced, while leverage effects were found to lead to explosive
volatility. In addition, investors were not rewarded for taking up additional risk since the risk premium
was insignificant for the full period. However, during explosive volatility, investors were rewarded for
taking up more risk. Moreover, we found that risk premium, leverage effects, and volatility persistence
were significantly correlated. The GARCH (1,1) and TGARCH(1,1) models were found to be the best
fit models to test for symmetric and asymmetric effects respectively. While the GARCH models were
able to provide evidence for the stylized facts in the NSE, we conclude that the presence or absence of
these features is period specific. This especially relates to volatility persistence, leverage effects, and
risk premium effects. Caution should, therefore, be taken in using a specific GARCH model to forecast
market return volatility in Kenya. It is thus imperative to pretest the data before any return volatility
forecasting is done.
