International Journal of Trade, Economics and Finance, Vol.1, No.4, December, 2010 2010-023X 387 Abstract—Stock market volatility is important in determining the cost of capital and to assess investment and leverage decisions since volatility is synonymous with risk. Risk-averse investors could be affected negatively due to substantial changes in volatility of the financial markets. We focus on the global crisis of 2007/2008 and its impact on the Malaysian financial market. We use GARCH models to model the volatility in order to determine the effect of the crisis on the KLCI. In order to be able to model the volatility, we first test the efficiency of the market using ARIMA models. We found that because of the financial crisis there was an increase in the impact of news about volatility from the previous periods but only a slight drop in the persistency of the conditional variance. Index Terms—Financial market, volatility forecasting, global financial crisis I. INTRODUCTION The end of 2007 and the beginning of 2008 witnessed the onset of global financial crisis which caused a havoc to the financial markets around the world. What started as a liquidity shortfall in the United States banking system, soon spread around the globe. Global security markets suffered huge losses and Malaysia was no exception. Between 14 January 2008 and 12 September 2008, a drop of around 670 points (which comes to about 45% of its value) was experienced by the KLCI, which was the main index and market indicator in Malaysia. Such a huge drop was last experienced during Asian financial crisis of 1997. However, when things started settling down, the general consensus was that the Asean countries were not very severely affected by the global financial crisis because of the precautions taken by these countries in securing their financial market after the Asian financial crisis. The question does arise then as to the size of the impact of the 2008 global financial crisis on the stock market volatility. The main objective of this study is thus to investigate the volatility of the Bursa Malaysia with regards to the recent financial crisis of 2007/2008, after the Asian financial crisis 1997. II. LITERATURE REVIEW Changes in volatility are a huge concern to investors and regulators alike. Several studies have been conducted and methodologies constructed in the attempt to model these Amir Angabini, Faculty of Mangement, Multimedia University, Cyberjaya, Malaysia, amir_2005641@yahoo.com Shaista Wasiuzzaman, Faculty of Management, Multimedia University, Cyberjaya, Malaysia, shaista@mmu.edu.my changes and the ARCH/GARCH family of models has been shown to be the best so far. ARCH effects are documented in the finance literature by Hsieh [1] for five different US dollar rates, Akgiray [2] for index returns, Schwert [3] for future markets, and Engle and Mustafa [4] for individual stock returns. Diebold [5], Baillie and Bollerslev [6] and Drost and Nijman [7] found that ARCH effects, which are highly significant with daily and weekly data, weaken as the frequency of the data decreases. Diebold and Nerlove [8] try to explain the existence of ARCH effects in the high frequency data due to the amount of information or the quality of the information reaching the markets in clusters or the time between information arrival and the processing of information by market participants. Brailsford and Faff [9] argue that volatility forecasting is very difficult and though in their study ARCH models and simple regression provided superior forecasting ability, the models were „sensitive to the error statistic used to assess the accuracy of the forecasts‟. Brooks et al. [10] support the applicability of the ARCH-GARCH models to South- African stock data. However, Barucci and Reno [11] find that GARCH models have better forecasting properties when Fourier analysis is used to calculate the diffusion process volatility, instead of the cumulative squared intraday returns. Rijo [12] also find that the GARCH(1,1) model gives the best fit for the National Stock Exchange (NSE) of India. Radha and Thenmozhi [13] forecast short term interest rate using ARMA, ARMA-GARCH and ARMA-EGARCH on the Indian market. Their results show that GARCH based models are more appropriate for forecasting than the other models. Padhi [14] uses the ARCH, GARCH and ARCH-in- mean models to explain the stock market volatility of the Indian market at the individual script level and at the aggregate indices level. The analysis reveals the same trend of volatility in the case of aggregate indices and five different sectors and the GARCH (1, 1) model is persistent for all the five aggregate indices and individual companies. The study on the effect of the global financial crisis on stock return volatility in India by Mishra [15] on the S&P CNX Nifty using GARCH models concludes the persistence of stock return volatility and its asymmetric effect. Ederington and Guan [16] compare the forecasting ability of various volatility forecasting models and find that the GARCH(1,1) model „generally yields better forecasts than the historical standard deviation and exponentially weighted moving average models..‟ but some reservations are still there in terms of the forecasting accuracy. Awartani and Corradi [17] find that when allowing for asymmetries, the MODELING THE EFFECTS OF THE GLOBAL FINANCIAL CRISIS ON THE MALAYSIAN MARKET Amir Angabini and Shaista Wasiuzzaman