Usage
stseq(N, lnum, refe = NULL, func = NULL, dendat = NULL, h = NULL, Q = NULL,
kernel = "epane", weights = NULL, sig = rep(1, length(N)), support = NULL,
theta = NULL, M = NULL, p = NULL, mul = 3, t = rep(1, length(N)),
marginal = "normal", r = 0, mu = NULL, xi = NULL, Omega = NULL, alpha = NULL,
df = NULL, g = 1, base = 10)
Arguments
N
d-vector of integers >1; the size of the grid where the function is
evaluated
lnum
positive integer; the number of level sets from which the
transforms are calculated
refe
d-vector of real numbers; the reference point for the shape
trees; if refe=NULL, then the location of the maximum of the function will
be used
func
character; the name of the function, see the "pcf.func" for the
possibilities
dendat
n*d matrix of data; when the function is a kernel estimate one
gives the data as argument
h
postive real number; the smoothing parameter of the kernel estimate
kernel
"gauss" or "epane"; the kernel of the kernel estimate
weights
n vector of nonnegative weights, where n is the sample size;
sum of the elements of "weights" should be one;
these are the weights of a time localized kernel estimator
base
positve integer or NULL; the base of the logarithm, when the
logarithmic spacing is used for the level sets, if "base" is NULL, then the
level sets are equispaced