Library: | smoother |
See also: | denestp |
Quantlet: | denxestp | |
Description: | estimates a p-dimensional density by kernel density estimation. The computation uses WARPing. |
Usage: | fh = denxestp(x {,h {,K} {,v} }) | |
Input: | ||
x | n x p matrix, the data. | |
h | scalar or p x 1 vector, bandwidth. If not given, the rule of thumb bandwidth computed by denrotp is used (Scott's rule of thumb). | |
K | string, kernel function on [-1,1]^p. If not given, the product Quartic kernel "qua" is used. | |
v | m x p, values of the independent variable on which to compute the regression. If not given, a grid of length 100 (p=1), length 30 (p=2) and length 8 (p=3) is used in case of p<4. When p>=4 then v is set to x. | |
Output: | ||
fh | n x (p+1) or m x (p+1) matrix, the first p columns contain the grid or the sorted x[,1:p], the second column contains the density estimate on the values of the first p columns. |
library("smoother") library("plot") ; x = read("geyser") ; read data fh = denxestp(x) ; estimate density ; fh = setmask(fh,"surface") plot(fh) ; graph density estimate setgopt(plotdisplay,1,1,"title","ROTATE!")
The kernel density estimate for the Geyser data is computed using the Quartic kernel and bandwidth according to Scott's rule of thumb (default). The display shows the surface of the resulting function.
library("smoother") library("plot") ; x = read("bank2.dat") ; read data x = x[,4:6] ; columns 4 to 6 fh = denxestp(x,1.5,"qua") ; estimate density ; c =(max(fh[,4])-min(fh[,4])).*(1:4)./5 ; levels cfh= grcontour3(fh,c,1:4) ; contours plot(cfh) ; graph contours setgopt(plotdisplay,1,1,"title","ROTATE!")
The kernel density estimate for the last three variables of the Swiss banknote data is computed using the Quartic kernel and bandwidth h=1.5. The display shows a contour plot of the resulting function.