Dear all,
I have the following function
kdenor <- function(aa,q=NULL){
a=sample(aa,500,replace=F)
ab=quantile(a, p=0.75)-quantile(a, p=0.25)
h=(0.9*min(var(a),ab))/(1.34*n^(1/5))
if(is.null(q)) {
q = seq(min(a)-3*h, max(a)+3*h, length.out=length(a))
}
nx = length(a)
nq = length(q)
xmat = matrix(q,nq,nx) - matrix(a,nq,nx,byrow=TRUE)
denall= dnorm(xmat/h)/h
denhat = apply(denall,1,mean)
f<-denhat
f1<-median(f)
#das<-list(x=q, y=denhat, h=h)
#return(das)
}
f1<-kdenor(aa)
My interest is to obtain the estimate of the density at the median of the
sample data.
But the output of the current function doesn't provide the correct result.
Kindly help.
Regards.
--
Jakperik Dioggban (Student, PAUISTI)
PhD Mathematics (Statistics Option)
Determination is Key to Success
--
Jakperik Dioggban (Student, PAUISTI)
PhD Mathematics (Statistics Option)
Determination is Key to Success
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.
