The Effect of the Underlying Distribution in Hurst Exponent Estimation

摘要: In this paper, a heavy-tailed distribution approach is considered in order to explore the behavior of actual financial time series. We show that kind allows properly fit empirical stocks from S&P500 index. addition that, we explain detail why underlying random process under study should be taken into account before using its self-similarity exponent as reliable tool state whether series displays long-range dependence or not. Finally, model, no index persistent memory, whereas some them do present anti-persistent memory and most at all.