Abstract:
|
The use of volatility models to conduct volatility forecasting is gaining momentum in empirical literature. The performance of volatility persistence, as indicated by the estimated parameter, , in Stochastic Volatility (SV) model is typically high. Since future values in SV models are based on the estimation of the parameters, this may lead to poor volatility forecasts. Furthermore, this high persistence, as contended by some research scientists, is due to the structure in the volatility processes, which SV model cannot capture. Hidden Markov Models (HMMs) allow for periods with different volatility levels characterized by the hidden states. In this paper, there is a mixture of the HMMs and SV models, called HMM-SV models. Through empirical analysis, the proposed HMM-SV models do not only address the shift in volatility levels, but also, provide better volatility forecasts and establish an efficient forecasting structure for volatility modeling.
|