Financial market volatility modeling and forecasting is a
major concern of a number of recent studies. Volatility reflects
uncertainty that has implications for investment decisions, risk
management and indeed monetary policy of a country. Poon and
Granger (2003) have provided an excellent review of the literature
on volatility modeling. Poon and Granger have suggested further
research especially in the area of trading volume volatility. They
have argued that such research can lead to a better understanding
and modeling of returns distribution. Trading volume plays
a critical role in financial markets. It facilitates the price discovery
process, enables investors to share financial risk and ensures
that corporations can raise funds needed for future investment
(McKenzie and Henry, 2008). Finance theory provides ambiguous
predictions about trading volume prior to corporate announcements.
The relationship between return on stocks and the trading
volume is also unclear (Girard and Biswas, 2007). However, it is generally accepted that high stock market volume is associated
with volatile returns and stock prices are more likely to decline
on a high volume day (Campbell, Grossman, & Wang, 1993).
Lamoureux and Lastrapes (1990) have suggested that conditional
heteroskedasticity may be caused by a time dependent
arrival rate of information in the financial markets. They used the
daily trading volume as a proxy for the arrival of such information
and confirm its significance.4 Like asset returns, volume of trade
itself is volatile in nature. According toWang (1994)the behavior of
the trading volume is closely linked to the underlying heterogeneity
among investors.Moreover, when liquidity trading is exogenous
and inelastic with respect to price, as inKyle (1985), trading volume