lstseq.kern {denpro} | R Documentation |
Calculates a scale of kernel estimates corresponding to a scale of smoothing parmeters.
lstseq.kern(dendat, hseq, N, lstree = NULL, level = NULL, Q = NULL, kernel = "gauss", hw = NULL, algo = "leafsfirst", support = NULL)
dendat |
n*d matrix of real numbers; the data matrix |
hseq |
a vector of positive real numbers; the sequence should be monotonic |
N |
vector of d positive integers; the dimension of the grid where the kernel estimate will be evaluated; we evaluate the estimate on a regular grid which contains the support of the kernel estimate |
lstree |
if NULL, then level set trees are not calculated |
level |
NULL or a real number between 0 and 1; if NULL, then shape trees are not calculated; if number, then it is the level in percents of the maximum of the level sets for which the shape trees are calculated |
Q |
positive integer; needed only in the DynaDecompose algorithm, see parameter "algo"; the number of levels in the level set trees |
kernel |
"epane" or "gauss"; the kernel is either the Bartlett-Epanechnikov product kernel or the standard Gaussian |
hw |
positive integer; parameter for time localized kernel estimation; gives the smoothing parameter for the temporal smoothing |
algo |
"leafsfirst" or "dynadecompose" |
support |
2*d vector of reals gives the d intervals of a rectangular support; c(low1,upp1,...,lowd,uppd) |
A list with components
lstseq |
a list of level set trees |
pcfseq |
a list of piecewise constant functions |
stseq |
a list of shape trees |
hseq |
a vector of smoothing parameters corresponding to the members in the sequences |
Jussi Klemela
dendat<-sim.data(n=200,type="mulmod") h1<-0.9 h2<-2.2 lkm<-5 hseq<-hgrid(h1,h2,lkm) N<-c(16,16) estiseq<-lstseq.kern(dendat,hseq,N)