Application In Chinese Stock Market Risk Measurement Var Method

VaR technique is a new risk management method that has been developed in 1990's. Compared with traditional models, it is easy to understand and apply so as to have practical significance. There have been a lot of technological methods proposed since its introduction. But different model often deduces different VaR value. So it is quite necessary and realistic for us now to find appropriate methods to manage the risk of China stock market.This paper analyzes the accuracy of different evaluate method by combine theoretical analysis and empirical analysis together. We try to find more feasible method for evaluating the market risk of the Chinese stock market. The paper is divided into four parts.The first part is the the preface, including the study condition on VaR in the world, the frame of this paper, and etc; The second part introduces different methods of evaluating the market risk, and VaR is introduced as the key method; The third part compares six typical models of variance-covariance methods, and analyzes the accuracy of different evaluation methods with certain distribution and confidence degree. We evaluate VaR with GARCH, EGARCH, PARCH, GARCH-M, EGARCH-M, and PARCH-M model, and assume certain distribution, such as normal distribution, student-t distribution and generalized error distribution (GED), 18 methods in all, and two confidence degrees of 95% and 99%. We compare the estimations of VaR in an application to daily returns on the Shanghai Synthesis index and Shenzhen Component index. Loss Function Test is used to evaluate the accuracy of the VaR model in this paper. The last part gets the brief summary.The finding of this paper indicates that when assuming student-t distribution , we will evaluate the risk over the actuality; Under the assumption of GED distribution, the risk will be evaluated more accurately than normal distribution; PARCH (1,1) model under the assumption of GED has the best result in calculating the VaR of the Shanghai Synthesis index and Shenzhen Component index, and the model is more feasible for evaluating the Chinese stock market risk.