Volatility, thin trading and non-liniarities: an empirical approach for the BET Index during pre-crisis and post-crisis periods

Forecasting volatility is essential for the market participants and has an important impact on building trading strategies. Lately, financial markets have experienced an increased volatility, which has led to the development of a variety of techniques in forecasting volatility. The aim of this paper is to modeling volatility of the Romanian Stock Market, both for pre-crisis and post-crisis periods, using five models of the GARCH family: GARCH, IGARCH, FIGARCH, GARCH-M and TARCH. Our results show evidence of high persistence in volatility, long memory, leverage effect, non-liniarities in the Romanian Stock Market. (C) 2015 The Authors. Published by Elsevier B.V.