OSCV_Gauss_dens {OSCV} | R Documentation |
The OSCV function based on
, the one-sided Gaussian kernel, in the kernel density estimation (KDE) context.
Description
Computing the values of the -based OSCV function in the density estimation context. See Savchuk (2017).
Usage
OSCV_Gauss_dens(h, dat, stype)
Arguments
h |
numerical vector of bandwidth values, |
dat |
numerical vecror of data values, |
stype |
specifies (anticipated) smoothness of the density function. Thus, |
Details
Computing the values of the OSCV function for the given bandwidth vector and data vector
. The function is based on the one-sided Gaussian kernel
. The (anticipated) smoothness of the underlying density function is to be specified. Thus,
-
corresponds to the smooth density;
-
corresponds to the nonsmooth density.
It is usually assumed that the density is smooth if no preliminary information about its nonsmoothness is available. The function's minimizer h_OSCV_dens
is to be used without additional rescaling to compute the ultimate Gaussian density estimate.
Value
The vector of values of the OSCV function for the correponsing vector of values.
References
Savchuk, O.Y. (2017). One-sided cross-validation for nonsmooth densty functions, arXiv:1703.05157.
See Also
h_OSCV_dens
, OSCV_Epan_dens
, OSCV_LI_dens
, C_smooth
.
Examples
## Not run:
dat_norm=rnorm(300) #generating random sample of size n=300 from the standard normal density.
h_oscv=round(h_OSCV_dens(dat_norm,0),digits=4)
y=density(dat_norm,bw=h_oscv)
dev.new()
plot(y,lwd=3,cex.lab=1.7,cex.axis=1.7,cex.main=1.7,xlab=paste("n=100, h_OSCV=",h_oscv),
main="Standard normal density estimate by OSCV",ylim=c(0,0.45),xlim=c(-4.5,4.5))
u=seq(-5,5,len=1000)
lines(u,dnorm(u),lwd=3,lty="dashed",col="blue")
legend(0.75,0.4,legend=c("OSCV estimate","N(0,1) density"),lwd=c(3,3),lty=c("solid","dashed"),
col=c("black","blue"),bty="n",cex=1.25)
## End(Not run)