kde {ks} | R Documentation |
Kernel density estimate for 1- to 6-dimensional data.
kde(x, H, h, gridsize, supp=3.7, eval.points)
x |
matrix of data values |
H |
bandwidth matrix |
h |
scalar bandwidth |
gridsize |
vector of number of grid points |
supp |
effective support for standard normal is [-supp, supp ] |
eval.points |
points that density estimate is evaluated at |
For d > 1, the kernel density estimate is computed exactly i.e. binning
is not used. For d = 1, the binned estimator from the
KernSmooth
library is used.
For d = 1, 2, 3, if eval.points
is not specified, then the
density estimate is automatically computed over a grid whose
resolution is controlled by gridsize
(default is 101, 51 x 51
and 51 x 51 x 51 respectively).
For d > 3, eval.points
must be specified.
Kernel density estimate is an object of class kde
which is a
list with 4 fields
x |
data points - same as input |
eval.points |
points that density estimate is evaluated at |
estimate |
density estimate at eval.points |
H |
bandwidth matrix (>1-d only) or |
h |
scalar bandwidth (1-d only) |
Wand, M.P. & Jones, M.C. (1995) Kernel Smoothing. Chapman & Hall. London.
### univariate example data(unicef) fhat <- kde(unicef[,1], h=sqrt(944)) fhat <- kde(unicef[,1], H=944) ## same as above ### bivariate example data(unicef) H.pi <- Hpi(unicef, nstage=1) fhat <- kde(unicef, H=H.pi) ### 4-variate example library(MASS) data(iris) ir <- iris[,1:4][iris[,5]=="setosa",] H.scv <- Hscv(ir) fhat <- kde(ir, H=H.scv, eval.points=ir)