# Finding bandwith with cross validation method

I am trying out some methods for finding the optimal bandwith for a kernel density estimation in R. Now I stumbled across a post on R-bloggers

If I compute the Silvermann's rule of thumb bandwith for my data I get the following

1.06*sd(kurseu)*length(kurseu)^(-1/5)
[1] 2.171556


Now if I use the cross validation method I get complete different results

J=function(h){
fdach=Vectorize(function(x)
density(kurseu,from=x,to=x,n=1,bw=h)$y) fdachi=Vectorize(function(i) density(kurseu[-i],from=kurseu[i],to=kurseu[i],n=1,bw=h)$y)
F=fdachi(1:length(kurseu))
return(integrate(function(x) fdach(x)^2,-Inf,Inf)$value-2*mean(F))} optimize(J,interval=c(.1,1))$minimum
[1] 0.6299948


I have no idea why the results are so much different from each other