This thesis focus on Extreme value Theory (EVT) and the possible usefulness to evaluate magnitudes of the Dow Jones Industrial Index during the current financial crisis (2006-2012). I centralize the analysis on the generalized Pareto distribution (GPD) and estimate the parameters with several techniques. I find clusters of volatilty and combine both the Peaks over Threshold (POT) method and Hawkes self-exciting POT models for exceedances over a given threshold with marked dependent processes for estimating the tail of loss distributions. The corresponding models allow to adopt two risk measures in different quantiles to assess the expected frequency of the magnitude. I also make an introduction to some possible extensions of the presented models.
|Educations||MSc in Business Administration and Management Science, (Graduate Programme) Final Thesis|
|Number of pages||81|