I have the code for the bivariate Gaussian copula. It is written with
for-loops, it works, but I wonder if there is a way to vectorize the
function.
I don't see how outer() can be used in this case, but maybe one can
use mapply() or Vectorize() in some way? Could anyone help me, please?
## Density of Gauss Copula
rho <- 0.5 #corr
R <- rbind(c(1,rho),c(rho,1)) #vcov matrix
id <- diag(2)
gauss <- matrix(0,99,99)
u <- seq(0.01, 0.99, by=0.01)
for(i in 1:99){
for(j in 1:99){
xx <- t(t(c(qnorm(u[i]), qnorm(u[j]))))
gauss[i,j] <-
1/sqrt(1-rho^2)*exp(-0.5*t(xx)%*%(solve(R)-id)%*%xx)
}
}
persp(u, u, gauss, xlab="x1", ylab="x2", zlab="Density of Gauss Copula",
theta=320, phi=20, col="palegreen", ticktype="detailed")
--
Sergei
______________________________________________
R-help@r-project.org 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.
