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
predict.rqss.Rd
\name{predict.rqss}
\alias{predict.rqss}
\alias{predict.qss1}
\alias{predict.qss2}
\title{Predict from fitted nonparametric quantile regression smoothing spline models}
\description{
Additive models for nonparametric quantile regression using total
variation penalty methods can be fit with the \code{\link{rqss}}
function. Univarariate and bivariate components can be predicted
using these functions.
}
\usage{
\method{predict}{rqss}(object, newdata, interval = "none", level = 0.95, ...)
\method{predict}{qss1}(object, newdata, ...)
\method{predict}{qss2}(object, newdata, ...)
}
\arguments{
\item{object}{ is a fitted object produced by \code{\link{rqss}} }
\item{newdata}{ a data frame describing the observations at which
prediction is to be made. For qss components, newdata should
lie in strictly within the convex hull of the fitting data. Newdata
corresponding to the partially linear component of the model
may require caution concerning the treatment of factor levels, if any.}
\item{interval}{If set to \code{confidence} then a \code{level} confidence interval
for the predictions is returned.}
\item{level}{intended coverage probability for the confidence intervals}
\item{\dots}{ optional arguments }
}
\details{
For both univariate and bivariate prediction linear interpolation is
done. In the bivariate case, this involves computing barycentric
coordinates of the new points relative to their enclosing triangles.
It may be of interest to plot individual components of fitted rqss
models: this is usually best done by fixing the values of other
covariates at reference values typical of the sample data and
predicting the response at varying values of one qss term at a
time. Direct use of the \code{predict.qss1} and \code{predict.qss2} functions
is discouraged since it usually corresponds to predicted values
at absurd reference values of the other covariates, i.e. zero.
}
\value{
A vector of predictions, or in the case that \code{interval = "confidence")}
a matrix whose first column is the vector of predictions and whose second and
third columns are the lower and upper confidence limits for each prediction.
}
\author{ R. Koenker }
\seealso{ \code{\link{rqss}}
}
\examples{
n <- 200
lam <- 2
x <- sort(rchisq(n,4))
z <- exp(rnorm(n)) + x
y <- log(x)+ .1*(log(x))^2 + z/4 + log(x)*rnorm(n)/4
plot(x,y - z/4 + mean(z)/4)
Ifit <- rqss(y ~ qss(x,constraint="I") + z)
sfit <- rqss(y ~ qss(x,lambda = lam) + z)
xz <- data.frame(z = mean(z),
x = seq(min(x)+.01,max(x)-.01,by=.25))
lines(xz[["x"]], predict(Ifit, xz), col=2)
lines(xz[["x"]], predict(sfit, xz), col=3)
legend(10,2,c("Increasing","Smooth"),lty = 1, col = c(2,3))
title("Predicted Median Response at Mean Value of z")
%%keep objects for inspection : do not rm(x,y,z,xz,fit)
## Bivariate example -- loads pkg "tripack"
require(tripack)
require(akima)
data(CobarOre)
fit <- rqss(z ~ qss(cbind(x,y), lambda=.08),
data= CobarOre)
plot(fit, col="grey",
main = "CobarOre data -- rqss(z ~ qss(cbind(x,y)))")
T <- with(CobarOre, tri.mesh(x, y))
set.seed(77)
ndum <- 100
xd <- with(CobarOre, runif(ndum, min(x), max(x)))
yd <- with(CobarOre, runif(ndum, min(y), max(y)))
table(s <- in.convex.hull(T, xd, yd))
pred <- predict(fit, data.frame(x = xd[s], y = yd[s]))
contour(interp(xd[s],yd[s], pred),
col="red", add = TRUE)
}
\keyword{regression}
\keyword{smooth}
\keyword{robust}