In this paper an earnest attempt is made to model the conditional volatility of an emerging market using data from the Karachi Stock Exchange(recently changed the name to Pakistan Stock Exchange)(KSE).We have employed asymmetric models [such as E-GARCH(1,1),T-GARCH(1,1)and P-GARCH(1,1)] as well as symmetric models [such as ARCH(1),GARCH(1,1)and GARCH-M(1,1)] to 22 years' daily,weekly and monthly KSE 100 index returns series to explore the nature and different associated aspects of volatility.New empirical evidence suggests that all three returns series display a non-normal distribution with high kurtosis and properties of stationarity.Moreover,we find a high persistence of volatility and that contributed to the impact of shocks,observed in the present,running on for longer times on future returns.And finally,P-GARCH(1,1)for the daily returns series and the GARCH(1,1)model for the weekly data turned out to be most compatible for volatility modelling. |