Dear R-users,
I have been using the code below in order to verify how the CDF of a
skew-normal distribution was calculated:
library(sn)
s=seq(-30,30,by=0.1)
a<-matrix(nrow=length(s),ncol=5)
lambda=1
for(i in 1:length(s)){
a[i,1]=pnorm(s[i],mean=0,sd=1);
a[i,2]=T.Owen(s[i],lambda);
a[i,3]=a[i,5]-2*a[i,6];
a[i,4]=pnorm(s[i])-2*T.Owen(s[i],lambda);
a[i,5]=psn(s[i],shape=lambda);
}
>From the literature I was expecting the column 3, 4 and 5 to give me the
exact same results but it actually doesn't. There seem to be some
approximations for small values of x. Does anyone know where does this come
from?
Any help would be greatly appreciated,
Cheers,
Boris
[[alternative HTML version deleted]]
______________________________________________
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.
