13.05.2018 Views

merged

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Forcasting Volatility of Stock Prices Using Arch and Garch Models<br />

Muhammad Qurzainaen Bin Zulkifli<br />

Supervisor: Dr. Che Mohd Imran Bin Che Taib<br />

Bachelor of Science (Financial Mathematics)<br />

School of Informatics and Applied Mathematics<br />

This study analyzes the forecasting volatility of the stock prices in Malaysia. The daily<br />

data of KPJ berhad are observed starting from January 1, 2010 until December 31, 2015.<br />

Autoregressive Conditional Heteroscedasticity (ARCH) and Generalized Autoregressive<br />

Conditional Heteroscedasticity (GARCH) are used to model the variances of the stock<br />

prices. ARCH and GARCH models are also used in getting robust estimation since both of<br />

them required a large amount of data which makes they tend to fit the in-sample-data<br />

but they also tend to fall apart in the out-sample-data. Results found that GARCH<br />

performed better than ARCH model by measuring the statistical performances since the<br />

Mean Absolute Error (MAE), Mean absolute percentage error (MAPE), and Root Mean<br />

Square Error (RMSE) of GARCH is smaller than ARCH model.<br />

828 | UMT UNDERGRADUATE RESEARCH DAY 2018

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!