Forecasting risk in the Swedish stock market - an investigation of GARCH volatility models.
Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
The purpose of this thesis has been to investigate various conditional volatility models commonly used in forecasting financial risk within the field of Financial Econometrics. The models examined were the GARCH, GJR-GARCH and TGARCH models. The models ability to forecast the conditional variance was investigated by forecasting the conditional volatility in three of the major Swedish stock indexes, the OMXS30, NOMXMSC and NOMXSSC. The forecasted volatility was then used to forecast Value at Risk measurements. A measurement that today is used in the risk management of most financial houses around the globe. The models ability to forecast volatility and Value at Risk was then examined by Root Mean Squared Errors, Mean Absolute Percentage Errors and Kupiecs Unconditional Coverage test. Support were found for GJR-GARCH and GARCH models with Gaussian and GED distributions producing the most adequately fit forecasts and Value at Risk measures.
Place, publisher, year, edition, pages
ARCH, GARCH, GJR-GARCH, TGARCH, Conditional Volatility, Value at Risk, Stock Indexes
IdentifiersURN: urn:nbn:se:uu:diva-255465OAI: oai:DiVA.org:uu-255465DiVA: diva2:822234
Forsberg, Lars, Universitetslektor
Guvå, Tomas, Universitetslektor