Modeling long memory in the EU stock market: evidence from the STOXX 50 returns

Abstract

This paper examines the persistence behaviour of STOXX 50 returns. To this end, we estimated the GARCH, IGARCH and FIGARCH models based on a data set comprising the daily returns from January 5th, 1987 to December 27th, 2013. The results show that the long-memory in the volatility returns constitutes an intrinsic and empirically significant characteristic of the data and are, therefore, in consonance with previous evidence on the subject. Moreover, our findings reveal that the FIGARCH is the best model to capture linear dependence in the conditional variance of the STOXX 50 returns as given by the information criteria