摘要：This paper examines the well-known stylized facts of stock returns volatiliy in the Dhaka Stock Exchange (DSE) utilizing daily all share price index return data for the period of 02 January 1993 to 27 January 2013. In addition, the study explores the adequate volatiliy model for DSE. The results of the estimated MA(1)-GARCH(1,1) model reveal that the stock returns of DSE capture volatility clustering and the volatility is moderately persistent. The estimated MA(1)-EGARCH(1,1) model displays that the effect of bad news on stock market volatility is greater than the effect induced by good news. Hence, it is concluded that return series of DSE shows evidence of three common stylized facts namely, volatility clustering, leptokurtosis and the leverage effect. In the end, this study discovers that MA(1)GARCH(1,1) is the best model for modeling volatility of DSE stock returns in Bangladesh.
