Some New Methods On Value At Risk (VaR) In Money Market And Their Application

Value at Risk (VaR) is currently a prevailing risk manage tool. It has been applied to measure and predict financial risk by many bank and investment institution. VaR's main problem is to fit total distribution and deal with tailor, which meanwhile is a hot problem for internal financial scholar. About this problem, there are a lot of methods and means. This thesis start with the yield of Chinese Stock Market to study their VaR, including evaluation and prediction. Some principal results are as fellow:The 3rd chapter mainly studys some property of Laplace distribution and my national stock market return distribution. By analysis, it shows that Laplace distribution possesses important applied worthy in financial field.In the term of Extreme Value Theory, especially, extreme distribution-II, the 4th chapter amends power law regulation, which makes up parametric estimating problem of extreme value method. As these results, a new method to estimate VaR, based on Laplace & extreme value -II distribution is put forward. In last chapter, a new conception and model for VaR, based on prediction are brought forward. Finally, a kind of new kernel density estimating function, adapting to financial time series is employed to extend time series kernel density estimating model...