Modeling Market Volatility in Emerging Markets: The case of Daily Data in Amman Stock Exchange 1992-2004

This paper attempts to investigate the volatility of the Jordanian emerging stock market using daily observations from Amman Stock Exchange Composite Index (ASE) for the period from January 1, 1992 through December 31, 2004. Preliminary analysis of the data shows significant departure from normality. Moreover, returns and residuals show a significant level of serial correlation which is related to the conditional heteroskedasticity due to the time varying volatility. These results suggest that ARCH and GARCH models can provide good approximation for capturing the characteristics of ASE. The empirical analysis supports the hypothesis of symmetric volatility; hence, both good and bad news of the same magnitude have the same impact on the volatility level. Moreover, the volatility persists in the market for a long period of time, which makes ASE market inefficient; therefore, returns can be easily predicted and forecasted.