Charles Thuo
2014-Mar-08 08:13 UTC
[R] fitting the lognormal and binomial into a gumbel copula
require(copula)
# I specify the copula
gmb<-gumbelCopula(4,dim=2)
# The bivariate CDF is generated
myCDF<-mvdc(gmb,margins=c("lnorm","nbinom"),paramMargins=list(list(meanlog=11.69,sdlog=0.7781),list(mu=16,size=2.6)))
# A random sample of the bivariate risk data is generated as a matrix.
The univariate parameters had been fitted using fitdistrplus
y<-cbind(rlnorm(1000,11.69,0.7781),rnbinom(1000,mu=16,size=2.6))
# the model is fitted and runs
Fitted<-fitMvdc(x,myCDF,c(4,meanlog=12,sdlog=0.9,mu=16,size=3))
# but when i attempt to call the model i get the following error
Fitted
Error: object 'Fitted' not found
Why does this happen and the model runs
Charles.
[[alternative HTML version deleted]]