Mesure de risques : calcul de la Value-at-Risk et application à la gestion de portefeuilles

Our work aims to study the behavior of financial assets' returns and to measure the market risk. In order to model the tail of the distribution of assets' returns, we use power laws, which reveal more efficient than normal distributions and, most often, than stable laws. Using statistical tools adapted to power laws, we measure the Value-at-Risk (VaR) and we propose a new indicator for portfolio management.