A Research On Financial Market Risk With VaR Method

VaR (Value at Risk) is a new method developed in recent years to quantify market risk, the great popularity that this instrument has achieved is essentially due to its simplicity and practicability, it can reduce the risk associated with any portfolio to just a number, the loss associated to a given probability. Most of the banks, nonfmancial companies have adopted this method to manage their market risk soon after it was invented, in addition to the Basel Committee, the Bank for International Settlements and other official institutions. In fact, VaR has become the standard method to manage financial risk at present. Since China has joined WTO, its financial industry will have to be faced with the challenges from the world. So it is an important and urgent task to search for fitful methods and systems to manage risk.A deeper research has been done on VaR system in this paper, it has in detail analyzed the background, calculation principle, advantage and disadvantage of VaR model. Then, it profoundly studies the typical three methods for calculating VaR at present, gives overall compare and analysis about the three methods. Among them, Historical Simulation method has grown increasing popular in practice because it is very easy to be applied and also very intuitive to be understood. There are , however, two very obvious disadvantages in this method, the first is that all the returns within the time window are assumed to have the same distribution, thus the probability density function of the return series doesn't change through the time horizon, the second is that only static data in the past are used when computing VaR without considering the dynamic volatility of the market at present. To overcome these disadvantages, an improvement was introduced by Boudoukh and his copartner in 1998, empirical tests show a significant improvement using the improved method. However, their improvement does not pay enough attention to large positive returns when computing VaR, since both large negative returns and positive returns are potentially indicative of an increase in overall portfolio riskiness. In this paper, we come up with a new improvement based on Boudoukh's method, and empirical tests show that our method can get a better result than the former.