actins2019-09-27 15:58:20

请问用12题的解法，答案是93呢？ X-0.5%*250*10/sqr0.5%*99.5%*250*10=1.96，求出X是93？ 以下是12题的答案解析：The risk manager will reject the hypothesis that the model is correctly calibrated if the number x of losses exceeding the VaR is such that: (x – pT)/sqrt(p(1 – p)T) > 1.96 where p represents the failure rate and is equal to 1 – 98%, or 2%; and T is the number of observations, 252. Then 1.96 = two-tail confidence level quantile → x >1.96 × sqrt(2% × 98% × 252) + p×T = 9.40. So the maximum number of exceedances would be 9 to conclude that the model is calibrated correctly.