Looks like plenty of people have had this problem b4 you - incl myself. Might
be an issue with this function. I had better luck using the function in
QRMlib package (fit.tcopula.rank, etc). Though for some really large data
sets I had to fudge the function itself with noforce=FALSE on the Kendall
call and some removal of NaN and NA's.
Oden, Kevin wrote:>
> I am using R 2.5.0 on windows XP and trying to fit copula. I see the
> following code works for some users, however my code crashes on the
> chol. Any suggestions?
>
>
>
>> mycop <- tCopula(param=0.5, dim=8, dispstr="ex", df=5)
>
>> x <- rcopula(mycop, 1000)
>
>> myfit <- fitCopula(x, mycop, c(0.6, 10),
optim.control=list(trace=1),
> method="Nelder-Mead")
>
> Nelder-Mead direct search function minimizer
>
> function value for initial parameters = -1747.582044
>
> Scaled convergence tolerance is 2.6041e-05
>
> Stepsize computed as 1.000000
>
> Error in chol(x, pivot = FALSE) : the leading minor of order 2 is not
> positive definite
>
>
>
> Kevin D. Oden
>
> e: kevin.oden at wachovia.com <mailto:kevin.oden at wachovia.com>
>
>
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>
--
View this message in context:
http://www.nabble.com/fitCopula-tf3965203.html#a12488563
Sent from the R help mailing list archive at Nabble.com.