Marcin Fałdziński

ESTIMATION OF THE PROBABLE MAXIMUM LOSS BASED ON EXTREME VALUE THEORY FOR STOCK RETURNS

The probable maximum loss is a measure that originated on the insurance market, where it is applied for insurance portfolio analysis. This corresponds to the 20-80 rule, which states that in a well defined portfolio 20% of the individual claims is responsible for more than 80% of the total claim amount. The paper presented attempts to estimate the probable maximum loss for stock returns which are treated as portfolios of securities. The probable maximum loss proved to be a useful tool for risk analysis or/and other diagnostic purposes on capital markets, it should be noted; however, that it has its drawbacks as well.

Application of Modified POT Method with Volatility Model for Estimation of Risk Measures

The main aim of this paper is the presentation and empirical analysis of the new approach which combines volatility models with Peaks over Threshold method that comes from extreme value theory. The new approach is applied for estimation of risk measures (VaR and ES) in financial time series. For the empirical analysis the financial risk model evaluation was conducted. In this paper the POT method was compared with standard volatility models (GARCH and SV) in case of the conditional modeling.