开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)|3.2.5(安卓)APP下载

还是星宇好 · 2020年08月17日

问一道题:NO.PZ2016082406000083

问题如下:

A risk analyst is trying to estimate the credit VAR for a risky bond. The credit VAR is defined as the maximum unexpected loss at a confidence level of 99.9% over a one-month horizon. Assume that the bond is valued at $1,000,000 one month forward, and the one-year cumulative default probability is 2% for this bond. What is the best estimate of the credit VAR for the bond, assuming no recovery?

选项:

A.

$20,000

B.

$1,682

C.

$998,318

D.

$0

解释:

ANSWER: C

First, we have to transform the annual default probability into a monthly probability. Using (12%)=(1d)12{(1-2\%)}={(1-d)}^{12}, we find d=0.00168, which assumes a constant probability of default during the year. Next, we compute the expected credit loss, which is d×$1,000,000=$1,682d\times\$1,000,000=\$1,682. Finally, we calculate the WCL at the 99.9% confidence level, which is the lowest number \(CL_i\)such that P(CLCLi)99.9%P{(CL\leq CL_i)}\geq99.9\%. We have P(CL=0)=99.83%P{(CL=0)}=99.83\%; P(CL1,000,000)=100.00%P{(CL\leq1,000,000)}=100.00\%. Therefore, the WCL is $1,000,000, and the CVAR is $1,000,000$1,682=$998,318\$1,000,000-\$1,682=\$998,318.

老师问个弱弱的问题

这个历史法计算都是假设是贝努力分布嘛

比如三个债券

PD_A=0.05

PD_B=0.1

PD_C=0.2

假设AB违约C不违约的概率:0.05*0.1*(1-0.2)

既然是贝努力为啥不是3C2*0.05*0.01*(1-0.2)呢。


我的意思为啥不用C那个公式算?

什么情况才会用到C那个公式算?

2 个答案

袁园_品职助教 · 2020年08月24日

同学你好!

是的,没错

袁园_品职助教 · 2020年08月18日

同学你好!

AB违约C不违约的概率 = 0.05*0.1*(1-0.2) ,没错

用3C2表示三个里面有两个不违约(一个违约),至于是哪两个,不知道

  • 2

    回答
  • 0

    关注
  • 342

    浏览
相关问题

NO.PZ2016082406000083 $1,682 $998,318 $0 ANSWER: C First, we have to transform the annufault probability into a monthly probability. Using (1−2%)=(1−12{(1-2\%)}={(1-}^{12}(1−2%)=(1−12, we fin0.00168, whiassumes a constant probability of fault ring the year. Next, we compute the expectecret loss, whiis $1,000,000=$1,682times\$1,000,000=\$1,682$1,000,000=$1,682. Finally, we calculate the Wthe 99.9% confinlevel, whiis the lowest number \(CL_i\)suthP(CL≤CLi)≥99.9%P{(CL\leq CL_i)}\geq99.9\%P(CL≤CLi​)≥99.9%. We have P(CL=0)=99.83%P{(CL=0)}=99.83\%P(CL=0)=99.83%; P(CL≤1,000,000)=100.00%P{(CL\leq1,000,000)}=100.00\%P(CL≤1,000,000)=100.00%. Therefore, the Wis $1,000,000, anthe CVis $1,000,000−$1,682=$998,318\$1,000,000-\$1,682=\$998,318$1,000,000−$1,682=$998,318.不记得课上有提到过这个计算,可以具体讲一下吗?然后对应讲义具体的哪个部分?

2021-04-10 08:23 1 · 回答

A risk analyst is trying to estimate the cret Vfor a risky bon The cret Vis finethe maximum unexpecteloss a confinlevel of 99.9% over a one-month horizon. Assume ththe bonis value$1,000,000 one month forwar anthe one-yecumulative fault probability is 2% for this bon Whis the best estimate of the cret Vfor the bon assuming no recovery? $20,000 $1,682 $998,318 $0 ANSWER: C First, we have to transform the annufault probability into a monthly probability. Using (1−2%)=(1−12{(1-2\%)}={(1-}^{12}(1−2%)=(1−12, we fin0.00168, whiassumes a constant probability of fault ring the year. Next, we compute the expectecret loss, whiis $1,000,000=$1,682times\$1,000,000=\$1,682$1,000,000=$1,682. Finally, we calculate the Wthe 99.9% confinlevel, whiis the lowest number \(CL_i\)suthP(CL≤CLi)≥99.9%P{(CL\leq CL_i)}\geq99.9\%P(CL≤CLi​)≥99.9%. We have P(CL=0)=99.83%P{(CL=0)}=99.83\%P(CL=0)=99.83%; P(CL≤1,000,000)=100.00%P{(CL\leq1,000,000)}=100.00\%P(CL≤1,000,000)=100.00%. Therefore, the Wis $1,000,000, anthe CVis $1,000,000−$1,682=$998,318\$1,000,000-\$1,682=\$998,318$1,000,000−$1,682=$998,318. 老师如果题目叫你求得CVAR是小于99.83%,P(loss≤0)=99.83%,那么WCL=0,了嘛,CVAR=-EL

2020-10-14 10:23 1 · 回答

$1,682 $998,318 $0 ANSWER: C First, we have to transform the annufault probability into a monthly probability. Using (1−2%)=(1−12{(1-2\%)}={(1-}^{12}(1−2%)=(1−12, we fin0.00168, whiassumes a constant probability of fault ring the year. Next, we compute the expectecret loss, whiis $1,000,000=$1,682times\$1,000,000=\$1,682$1,000,000=$1,682. Finally, we calculate the Wthe 99.9% confinlevel, whiis the lowest number \(CL_i\)suthP(CL≤CLi)≥99.9%P{(CL\leq CL_i)}\geq99.9\%P(CL≤CLi​)≥99.9%. We have P(CL=0)=99.83%P{(CL=0)}=99.83\%P(CL=0)=99.83%; P(CL≤1,000,000)=100.00%P{(CL\leq1,000,000)}=100.00\%P(CL≤1,000,000)=100.00%. Therefore, the Wis $1,000,000, anthe CVis $1,000,000−$1,682=$998,318\$1,000,000-\$1,682=\$998,318$1,000,000−$1,682=$998,318.老师,我看了所有问题的回答还是没没明白99.83%是怎么算出来的还有怎么得出WCL是1,000,000。可以把讲义里这部分的内容帮忙粘贴一下吗?实在是很难和讲义对应上。

2020-09-20 16:51 1 · 回答

A risk analyst is trying to estimate the cret Vfor a risky bon The cret Vis finethe maximum unexpecteloss a confinlevel of 99.9% over a one-month horizon. Assume ththe bonis value$1,000,000 one month forwar anthe one-yecumulative fault probability is 2% for this bon Whis the best estimate of the cret Vfor the bon assuming no recovery? $20,000 $1,682 $998,318 $0 ANSWER: C First, we have to transform the annufault probability into a monthly probability. Using (1−2%)=(1−12{(1-2\%)}={(1-}^{12}(1−2%)=(1−12, we fin0.00168, whiassumes a constant probability of fault ring the year. Next, we compute the expectecret loss, whiis $1,000,000=$1,682times\$1,000,000=\$1,682$1,000,000=$1,682. Finally, we calculate the Wthe 99.9% confinlevel, whiis the lowest number \(CL_i\)suthP(CL≤CLi)≥99.9%P{(CL\leq CL_i)}\geq99.9\%P(CL≤CLi​)≥99.9%. We have P(CL=0)=99.83%P{(CL=0)}=99.83\%P(CL=0)=99.83%; P(CL≤1,000,000)=100.00%P{(CL\leq1,000,000)}=100.00\%P(CL≤1,000,000)=100.00%. Therefore, the Wis $1,000,000, anthe CVis $1,000,000−$1,682=$998,318\$1,000,000-\$1,682=\$998,318$1,000,000−$1,682=$998,318. 为什么会有WCL=0 的这个假设 P(CL=0) =99.83%, 所以只有可能等于1682 和0这两个可能性?这个地方没有看懂

2020-03-21 16:20 1 · 回答