Těžké chvosty a měřítka tržního rizika : na příkladu českého akciového trhu

Bulva, Radek

One of the stylized facts about the behaviour of financial returns is that they tend to exhibit more probability mass in the tails of the distribution than would be suggested by the normal distribution. This phenomenon is called heavy tails. The first part of this thesis focuses on examining the tails of a distribution of returns to Czech stock market index PX. Parametric and semi-parametric approaches to estimation of the tail index, a measure of heaviness of tails, are applied and compared. The results indicate that the tails behave in a way one would expect from emerging market stock index. In the second part of the thesis, we introduce two simple measures of market risk, Value at Risk and Expected Shortfall, and compare traditional methods of their estimation with methods adjusted for presence of heavy tails. We conclude that reliance on the normal distribution in modelling the returns can lead to serious underestimation of risks inherent in the underlying process.

host :: přihlásit Digitální repozitář
		Hledej		Nový záznam		Nápověda		O repozitáři