Mohammad Javad Mohagheghnia; Kashi Mansoor; Alireza Daliri; Mohammad Donyaei
Volume 12, Issue 33 , July 2015, , Pages 151-181
Abstract
This paper investigates the presence of long memory in the Tehran stock market, using the ARFIMA, GPH, GSP and FIGARCH models. The data set consists of daily returns, and long memory tests are carried out both for the returns and volatilities of TEPIX series. Results of the GPH, GSP and ARFIMA models ...
Read More
This paper investigates the presence of long memory in the Tehran stock market, using the ARFIMA, GPH, GSP and FIGARCH models. The data set consists of daily returns, and long memory tests are carried out both for the returns and volatilities of TEPIX series. Results of the GPH, GSP and ARFIMA models indicate the existence of long memory in return series. Also, suggest that long memory dynamics in the returns and volatility might be modeled by using the ARFIMA–FIGARCH model. Furthermore, results of this model shoes the strong evidence of long memory, both in conditional mean and conditional variance. In addition, the assumption of non-normality is appropriate for capturing the asymmetry and tail fatness of estimated residuals. These findings suggest that the model based on the Gaussian normality assumption may be inappropriate for modeling the long memory property. Finally, it seems that the Tehran Stock Exchange (TSE) cannot be considered an efficient market in terms of the speed of information transmission. Hence, speculative earnings could be gained via predicting stock prices.
