[R] HOW TO SOLVE THIS PROBLEM (RVALS)

[Rui Barradas]

Hello,

nobs is missing in your example.

Assuming that envelope is the function in package base boot, I cannot 
reproduce the error.


set.seed(2021)
nc <- 10000
nobs <- 100
M1 <- matrix(evd::rfrechet(nc*nobs),nrow=nobs,ncol=nc)
M <- t(apply(M1,2,sort))
E <- boot::envelope(mat=M) #compute 95% confidance bands

str(E)
#List of 7
# $ point  : num [1:2, 1:100] 0.302 0.12 0.341 0.167 0.373 ...
# $ overall: num [1:2, 1:100] 0.3698 0.0832 0.4163 0.1287 0.4499 ...
# $ k.pt   : num [1:2] 250 9751
# $ err.pt : num [1:2] 0.05 0.562
# $ k.ov   : num [1:2] 11 9990
# $ err.ov : num [1:2] 0.0022 0.0496
# $ err.nom: num [1:2] 0.05 0.05


Hope this helps,

Rui Barradas


Às 08:53 de 07/08/21, SITI AISYAH ZAKARIA escreveu:
> Hi,
> 
> Can anyone help me how to solve this problem?
> 
>   #calculation of confidence intervals
> 1. > nc <- 10000
> 2. > M1 <- matrix(rfrechet(nc*nobs),nrow=nobs,ncol=nc)
> 3. > M <- t(apply(M1,2,sort))
> 4. > E <- envelope(mat=M) #compute 95% confidance bands
> *Error in envelope.matrix(mat = M) : rvals must be supplied*
> 
> My problem is after I run my coding in line 4 the error is highlighted red
> is come out. I don't know how to solve it. Please help me.
> 
> Thank you
>