NO.PZ2018122701000037
问题如下：
A risk manager is analyzing a 1-day 99% VaR model. Assuming 225 days in a year, what is the maximum number of daily losses exceeding the 1-day 99% VaR that is acceptable in a 1-year backtest to conclude, at a 95% confidence level, that the model is calibrated correctly?
选项：
A.3
B.5
C.8
D.10
解释：
B is correct.
考点:Backtesting VaR
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:
where p represents the failure rate and is equal to 1 - 99%, or 1%; and T is the number of observations = 225. And z = 1.96 is the two-tail confidence level quantile. If:
Then, x = 5.18. So the maximum number of exceedances would be 5 to conclude that the model is calibrated correctly.
95%的双尾检验对应的分位点不是1.65嘛，解析用的是1.96那不变成单尾了
