| Summary: | Stock return volatility has been shown to occasionally exhibit discrete structural shifts. These shifts are particularly evident in the transition from ‘normal’ to crisis periods, and tend to be more pronounced in developing markets. This study aims to establish whether accounting for structural changes in the conditional variance process, through the use of Markov-switching models, improves estimates and forecasts of stock return volatility over those of the more conventional single-state (G)ARCH models, within and across selected African markets for the period 2002-2012. In the univariate portion of the study, the performances of various Markov-switching models are tested against a single-state benchmark model through the use of in-sample goodness-of-fit and predictive ability measures. In the multivariate context, the single-state and Markov-switching models are comparatively assessed according to their usefulness in constructing optimal stock portfolios. It is found that, even after accounting for structural breaks in the conditional variance process, conventional GARCH effects remain important to capturing the heteroscedasticity evident in the data. However, those univariate models which include a GARCH term are shown to perform comparatively poorly when used for forecasting purposes. Additionally, in the multivariate study, the use of Markov-switching variance-covariance estimates improves risk-adjusted portfolio returns when compared to portfolios that are constructed using the more conventional single-state models. While there is evidence that the use of some Markov-switching models can result in better forecasts and higher risk-adjusted returns than those models which include GARCH effects, the inability of the simpler Markov-switching models to fully capture the heteroscedasticity in the data remains problematic.
|
|---|
