Efficiency of the markov regime switching GARCH Model in modelling volatility for tea prices

Abstract

This study examines the ability of the Markov Regime Switching GARCH model, in comparison with the univariete GARCH models, in modelling and forecasting price volatility of the tea traded at the Mombasa Tea Auction within some time horizon. The study uses weekly data, from 2010 to 2017, to analysis regime switching in volatility and provides an in-sample and out-of-sample forecast. Volatility regime switching is first modelled with a Markov switching framework. In-sample and out-of-sample forecasts of volatility using competing MRS-GARCH models and the single regimes GARCH models are then provided. Comparison of in-sample forecast is done on the basis of goodness-of-fit and the comparison of the out-of-sample forecasts is done on the basis of forecast accuracy, using the statistical loss function. The results show that the MRS-GARCH models can remove the high persistence of GARCH models. This shows the priority of MRS-GARCH models and provides evidence of regime clustering. In out-of-sample forecast perfomance, the MRS-GARCH models were better than the single regime GARCH model. However, this superioirity fades for longer time horizon.