Long Memory Features in Return and Volatility of the Malaysian Stock Market

This study aims to investigate the existence of long memory in the Malaysian stock market utilizing daily stock price index from the period 1998:09 to 2009:12. Various ARFIMA-G(ARCH)-type models have been taken into consideration to address this issue, which has led to several interesting conclusions. Firstly, the long memory property exists in both the return and volatility, with and without incorporating the crisis impact. Secondly, the stock volatility is found to be experiencing significant leverage effect especially with the inclusion of the impact of crisis. This implies that the volatility has the tendency to respond to bad news more than good news as compared to the other periods under study. Thirdly, among the various G(ARCH)-type models with different innovation distributions, the Student-t distribution provides better specifications in terms of the long memory volatility processes. In summary, ARFIMA-FIAPARCH model is found to be the most appropriate method of presenting the stylized facts of stock return and volatility in Malaysia.