swh:1:snp:a3b81a63bc885946c7e57d5f25f804425977c98d
Tip revision: 5ad24cff87e41a020a678cf6e742678aa2ee9dce authored by Roger Koenker on 29 May 2018, 10:33:02 UTC
version 5.36
version 5.36
Tip revision: 5ad24cf
qss.Rd
\name{qss}
\alias{qss}
\alias{qss1}
\alias{qss2}
\alias{triogram.fidelity}
\alias{triogram.penalty}
\title{Additive Nonparametric Terms for rqss Fitting}
\description{
In the formula specification of \code{rqss} nonparametric terms
are specified with \code{qss}. Both univariate and bivariate
specifications are possible, and qualitative constraints may also be specified
for the qss terms.
}
\usage{
qss(x, constraint = "N", lambda = 1, ndum = 0, dummies = NULL, w = rep(1, length(x)))
}
\arguments{
\item{x}{The covariate determining the nonparametric component, if
x is a matrix with two columns then the qss
function will construct a penalized triogram term.}
\item{lambda}{The smoothing parameter governing the tradeoff between
fidelity and the penalty component for this term. Larger lambdas
produce smoother fits. In future
versions there should be an automatic mechanism for default
choice of the lambdas. For now, this is the responsibility
of the user.}
\item{constraint}{Optional specification of qualitative constraints
on the fitted univariate qss functions, take the values: "N","I","D","V","C"
"VI","VD","CI","CD" for none, increasing, decreasing, convex,
concave, convex and increasing, etc. And for bivariate qss
components can take the values "N","V","C" for none, convex, and concave.
Note that confidence bands for constrained fits of this sort, while
available from \code{plot.rqss} as of yet lack a formal justification.}
\item{ndum}{number of dummy vertices: this is only relevant for qss2
terms. In addition to vertices at the observed (x,y) points
ndum dummy vertices are generated -- distributed uniformly over
the rectangle given by the Cartesian product of the ranges of
x and y -- observations that fall in the convex hull of the
observations are retained. So the actual number of dummy
vertices used is smaller than ndum. The values of these
vertices are returned in the list dummies, so that they can
be reused.}
\item{dummies}{list of dummy vertices as generated, for example by
triogram.fidelity when ndum > 0. Should be a list with x
and y components. These points should lie inside the convex
hull of the real xy points, but no explicit checking of this
assertion is currently done.}
\item{w}{ weights not yet unimplemented }
}
\details{
The various pieces returned are stored in sparse matrix.csr form.
See \code{\link{rqss}} for details on how they are assembled. To preserve the
sparsity of the design matrix the first column of each qss term is dropped.
This differs from the usual convention that would have forced qss terms
to have mean zero. This convention has implications for prediction that need to be
recognized. The penalty components for qss terms are based on total
variation penalization of the first derivative (and gradient, for bivariate x)
as described in the references appearing in the help for \code{rqss}.
For the bivariate case, package \pkg{tripack} (and for plotting also
\pkg{akima}) are required (automatically, by the \R code).
}
\value{
\item{F}{Fidelity component of the design matrix}
\item{dummies}{List of dummy vertices}
\item{A}{Penalty component of the design matrix}
\item{R}{Constraint component of the design matrix}
\item{r}{Constraint component of the rhs}
}
\author{Roger Koenker}
\seealso{ \code{\link{rqss}}}
\keyword{smooth}
\keyword{robust}