Stock market risk measured by VaR nad CVaR: A comparison study

VaR and CVaR are effective quantitative measurement of market risk. These measures can quantify the risk unexpected changes within a given period. In this paper, we examine risk of four stock indices: Czech PX, Austrian ATX, London FTSE, American S&P 500. First, returns these indices approximated using two distributions showing semi-heavy tails: t- distribution normal inverse Gaussian distribution. For comparison, empirical distributions also included since they often work as convenient alternatives. Subsequently, VaR99 and CVaR97.5 values corresponding to candidate calculated for each index. We also analyze ability theoretical distribution approximate left tail behavior market indices returns. It turns out that is not suitable purpose. Furthermore, it appears higher (in absolute value) all than 99, which may require need economic capital, which banks should allocate.