Revision 06a935fcd0daca8842f0d3138ff354753033c0ec authored by Thomas Nagler on 11 May 2021, 23:50:12 UTC, committed by cran-robot on 11 May 2021, 23:50:12 UTC
1 parent 950ccc0
kde1d.Rd
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/kde1d.R
\name{kde1d}
\alias{kde1d}
\title{Univariate kernel density estimation for bounded and unbounded support}
\usage{
kde1d(x, mult = 1, xmin = -Inf, xmax = Inf, bw = NULL,
bw_min = 0, ...)
}
\arguments{
\item{x}{vector of length \eqn{n}.}
\item{mult}{numeric; the actual bandwidth used is \eqn{bw*mult}.}
\item{xmin}{lower bound for the support of the density.}
\item{xmax}{upper bound for the support of the density.}
\item{bw}{bandwidth parameter; has to be a positive number or \code{NULL};
the latter calls \code{\link[KernSmooth:dpik]{KernSmooth::dpik()}}.}
\item{bw_min}{minimum value for the bandwidth.}
\item{...}{unused.}
}
\value{
An object of class \code{kde1d}.
}
\description{
Discrete variables are convoluted with the uniform distribution (see, Nagler,
2017). If a variable should be treated as discrete, declare it as
\code{\link[=ordered]{ordered()}}.
}
\details{
If \code{xmin} or \code{xmax} are finite, the density estimate will
be 0 outside of \eqn{[xmin, xmax]}. Mirror-reflection is used to correct
for boundary bias. Discrete variables are convoluted with the uniform
distribution (see, Nagler, 2017).
}
\examples{
data(wdbc, package = "kdecopula") # load data
fit <- kde1d(wdbc[, 5]) # estimate density
dkde1d(1000, fit) # evaluate density estimate
}
\references{
Nagler, T. (2017). \emph{A generic approach to nonparametric function
estimation with mixed data.} \href{https://arxiv.org/abs/1704.07457}{arXiv:1704.07457}
}
\seealso{
\code{\link{dkde1d}}, \code{\link{pkde1d}}, \code{\link{qkde1d}},
\code{\link{rkde1d}} \code{\link{plot.kde1d}} , \code{\link{lines.kde1d}}
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...