regpro (version 0.1.1)

pcf.kernesti.slice: A slice of a multivariate kernel regression estimator

Description

Computes the values of a univariate slice of multivariate kernel regression estimator (Nadaraya-Watson estimator) on a regular grid.

Usage

pcf.kernesti.slice(x, y, h, N, kernel="gauss", coordi=1, p=0.5, 
center=NULL, direc=NULL, radius=NULL)

Arguments

x

n*d data matrix; the matrix of the values of the explanatory variables

y

n vector; the values of the response variable

N

vector of d positive integers; the number of grid points for each direction

h

a positive real number; the smoothing parameter of the kernel estimate

kernel

a character; determines the kernel function; either "gauss" or "uniform"

coordi

integer 1,...,d; the direction of the slice

p

0

center

either NULL or a d-vector; gives the point which is intersected by the slice

direc

either NULL or a d-vector; gives the direction of the slice

radius

either NULL or a positive real number; gives the radius of the slice

Value

See Also

kernesti.regr,

Examples

n<-100
d<-2 
x<-8*matrix(runif(n*d),n,d)-3
C<-(2*pi)^(-d/2)
phi<-function(x){ return( C*exp(-sum(x^2)/2) ) }
D<-3; c1<-c(0,0); c2<-D*c(1,0); c3<-D*c(1/2,sqrt(3)/2)
func<-function(x){phi(x-c1)+phi(x-c2)+phi(x-c3)}
y<-matrix(0,n,1)
for (i in 1:n) y[i]<-func(x[i,])+0.01*rnorm(1)

num<-30  # number of grid points in one direction
pcf<-pcf.kernesti.slice(x,y,h=0.5,N=num)

dp<-draw.pcf(pcf,minval=min(y))
plot(dp$x,dp$y,type="l")