Dear Dr. Martin,
I'm glad that you replied to my queries.
As advised, I have prepared the following:
library(copula)
# 5 series of data, A, B, C, D and E
A <- c(0.849420849, 0.900652985, 0.97144217, 0.817888428, 0.877901578,
1.070040669, 0.889742431, 0.87588968, 0.853541938, 0.848664688,
0.876830319, 0.749582638, 0.818515498, 0.890997174, 0.794766966,
0.784794851, 0.814858959, 1.074396518, 0.83752495, 0.894341116,
0.880375293, 0.900816803)
B <- c(0.479850746, 0.652111668, 1.880607815, 0.579902303, 0.50669344,
0.747560182, 0.701754386, 0.48969697, 0.346751006, 0.379234973,
0.862691466, 0.328280188, 0.317312661, 0.534438115, 0.487002653,
0.335043612, 0.373346897, 0.627520161, 0.792114695, 0.938253012,
0.444553967, 0.625972763)
C <- c(0.693491124, 0.866523143, 4.585714286, 1.512055109, 0.387755102,
0.513435701, 0.76252505, -0.113113113, 0.338521401, 0.333951763,
0.668755595, 0.401273885, 0.419868791, 0.272885789, 0.541541542,
0.32751938, 0.386409736, 0.957446809, 0.861195542, 1.531632653,
0.431610942, 1.226470588)
D <- c(0.807792208, 0.548547718, 0.738232865, 0.542247744, 1.088964927,
0.862385321, 0.60720268, 1.000816993, 0.699289661, 0.41723356,
0.604037267, 0.605003791, 0.698940998, 0.764792899, 0.647897898,
0.825256975, 0.767476085, 0.941391941, 0.889547813, 0.324503311,
0.942435424, 0.740686633)
E <- c(1.077598829, 0.318507891, 1.152616279, 0.930397727, 1.515994437,
0.940689655, 0.880886427, 1.054274084, 1.067282322, 0.677419355,
0.966233766, 0.761029412, 1.05734767, 0.615925059, 1.061988304,
1.07184241, 1.058890147, 1.123873874, 1.304891923, -0.069584736,
1.172757475, 0.501096491)
gumbel.copula <- gumbelCopula(dim = 2)
p <- pobs(as.matrix(cbind(D + E, A + B+ C )))
fit.gumbel <- fitCopula(gumbel.copula, p, method = "ml") #The error is here
when trying to fit the gumbel copula
# I got the following error:
Error in optim(start, loglikCopula, lower = lower, upper = upper, method =
method, :
non-finite finite-difference value [1]
In addition: Warning message:
In .local(copula, tau, ...) : tau is out of the range [0, 1]
#Due to error in fitting the gumbel copula, this step can't be processed
coef(fit.gumbel)
gofCopula(gumbel.Copula, p, estim.method = "mpl", method = "Sn", simulation
= "mult")
Thanks in advance!
Best regards,
Isaudin
On Wed, Aug 10, 2016 at 5:08 PM, Martin Maechler <maechler at stat.math.ethz.ch
wrote:
Isaudin Ismail <isaudin at gmail.com>
on Tue, 9 Aug 2016 14:30:18 +0100 writes:
> Dear R experts,
> I have 5 time series of data (A, B, C, D and E) with all same
lengths. All
> series exhibit gamma distribution except for B which is lognormal
> distribution. I am using copula package to model the
joint-distribution of
> these 5 times series.
> I have selected Archimedean copula and successfully fitted Frank and
> Clayton copula. The problem is when trying to fit Gumbel copula.
> The following are the codes I used to run in R.
> # Data of 5 time series
> A <- A
> B <- B
> C <- C
> D <- D
> E <- E
well, the above is really an "interesting" block of R code ;-)
--
More seriously, please learn to use reproducible examples,
e.g., from here
http://bit.ly/MRE_R (nice to remember: MRE = Minimal Reproducible
Example)
or here
http://adv-r.had.co.nz/Reproducibility.html
then we will be glad to help you,
notably I as maintainer of the package 'copula' which you are
using (without saying so).
With regards,
Martin Maechler
> # Combined between A and C
> A+C <- A + C
> gumbel.copula <- gumbelCopula(dim = 5)
> m <- pobs(as.matrix(cbind(A+C, B, D, E)))
> fit.gumbel<- fitCopula(gumbel.copula, m, method = 'ml')
> And the error while trying to fit gumbel copula: