关于下标出界的问题！！！

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

在使用creditmetrics软件包时提示下标出界，请高手指教
N<-4
n<-100000
r<-0.025
ead<-c(320,1300,150,34)
rc<-c(“AAA”,”AA”,”A”,”BBB”,”BB”,”B”,”CCC”,”D”)
lgd<-0.3873
rating<-c(“AAA”,”AA”,”BB”,”C”)
loadnames<-c(“Load1”,”Load2”,”Load3”,”Load4”)
alpha<-0.99
rho<-matrix(c(1,0.625,-0.7619,-0.7202,0.625,1,-0.7679,-0.7857,-0.7619,-0.7679,1,0.5893,-0.7202,-0.7857,0.5893,1),4,4,dimnames=list(loadnames,loadnames),byrow=TRUE)
M<-matrix(c(97.12,2.58,0.18,0.02,0.03,0.01,0.06,0,2.85,89.73,6.68,0.49,0.05,0.08,0.06,0.06,0.1,2.16,91.43,5.42,0.4,0.17,0.07,0.25,0.03,0.14,3.66,89.63,4.47,0.73,0.52,0.82,0.08,0.05,0.2,6.3,81.79,6.59,2.29,2.7,0,0.03,0.16,0.27,3.94,70.43,19.21,5.96,0,0,0.07,0.1,0.29,3.73,67.83,27.98,0,0,0,0,0,0,0,100)/100,8,8,dimnames=list(rc,rc),byrow=TRUE)cm.CVaR(M,lgd,ead,N,n,r,rho,alpha,rating)
错误: 下标出界
此外: 警告信息：
In qnorm(p, mean, sd, lower.tail, log.p) : 产生了NaNs

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：metrics Metric Credit RICS ITME 标出

不是你的问题,是floating-accuracy
问题出在cumMPRev[3,8]

rc<-c("AAA","AA","A","BBB","BB","B","CCC","D")
M<-matrix(c(97.12,2.58,0.18,0.02,0.03,0.01,0.06,0,2.85,89.73,6.68,0.49,
0.05,0.08,0.06,0.06,0.1,2.16,91.43,5.42,0.4,0.17,0.07,0.25,0.03,0.14,
3.66,89.63,4.47,0.73,0.52,0.82,0.08,0.05,0.2,6.3,81.79,6.59,2.29,2.7,
0,0.03,0.16,0.27,3.94,70.43,19.21,5.96,0,0,0.07,0.1,0.29,3.73,67.83,
27.98,0,0,0,0,0,0,0,100)/100,8,8,dimnames=list(rc,rc),byrow=TRUE)

cm.matrix(M)
mpRev <- M[1:(dim(M)[1] - 1), dim(M)[2]:1]
cumMPRev <- t(apply(mpRev, 1, cumsum))
cumMPRev
q <- qnorm(cumMPRev[3,8])   
#In qnorm(p, mean, sd, lower.tail, log.p) :  ...NaNs
1== cumMPRev[3,8]
#[1] FALSE
sprintf("%.30f",cumMPRev[3,8])
#[1] "1.000000000000000222044604925031" > 1

看不太懂。。。是精确度的问题吗？如何解决呢？请高手指教