Var Measurement And Empirical Research Based On EGARCH Model

Financial risks management is a hot topic in financial institutions,academia,and financial supervisors. Risks measurement is the core of effective risks management. Therefore,it is significantly important to study risks measurement in the background of financial globalization. Reasonable risks measurement is fundamental for Chinese risk management study.Now,the value at risk(Var) has been widely applied in the financial risk measurement.The risk measurement set its basis on statistic and mathematical algorithms,combined with marketable movement.Experience has shown that the assumption based on normal distribution can not handle the financial variables in the fat tail, while t distribution and generalized error distribution can deal with the problem very well.In this paper,taking our country spot gold(AU99.95) for the study, using EGARCH model, we study the price volatility in normal distribution, t distribution and the generalized error distribution respectively. The results show that:there are existence of clustering,heteroskedasticity and leveraged in the price volatility of our country spot gold(AU99.95), and the fitting effect of t distribution and generalized error distribution are better than normal.