Modeling And Forecasting of Return Volatility in Russian Stock Market Using GARCH Model

The aim of this research is to determine the most preferable GARCH model for volatility estimation of MICEX index return and of Russian companies’ stocks returns. There were tested three modifications of GARCH models, in particular, GARCH (1,1), EGARCH (1,1) and GJR-GARCH (1,1,1). For MICEX index the best model for volatility estimation that outperforms the other is EGARCH (1,1) model. For Russian companies the results are different, and the unique preferred model for all companies was not found. The forecasting ability of all models is weak, and the best fitted model appears to be different from that, which gives the best volatility forecasting. The first two chapters of this graduation paper consider the concept of volatility and the models used for its estimation. In the third chapter the application of existing models for volatility estimation was conducted for the MICEX index and Russian companies’ stocks returns.