Abstract:
Investors and policymakers need to be aware of fluctuations in stock
returns to manage portfolio adjustments and risk management decisions. Therefore, it
is crucial to capture volatility, which is a measure of how strongly the price of a security
clusters around the mean. The study used information from Yahoo Finance, a leading
website of financial data and had applied the proposed methodology to one stock from
each of the eleven industries in which they had separately represented the data. This
project offers an approach to determine the best forecasting GARCH model among
GARCH, EGARCH and GJR-GARCH that may be used to predict financial volatility of
stocks. The study also used the Generalized Error Distribution, Students t Distribution,
and Skewed Student t Distribution as error distributions in addition to the normal
distribution. The identified models and error distributions that provided the significant
parameters, were further forecasted using rolling window forecast and by relying on
Root Mean Square error the best model had been selected.
