The R Project SVN R

% file lqs/man//predict.lqs.Rd
% copyright (C) 1999 B. D. Ripley
%
\name{predict.lqs}
\alias{predict.lqs}
\title{
Predict from an lqs Fit
}
\description{
Predict from an resistant regression fitted by \code{lqs}.
}
\usage{
predict.lqs(object, newdata)
}
\arguments{
\item{object}{
object inheriting from class \code{lqs}
}
\item{newdata}{
matrix or data frame of cases to be predicted or, if object
has a formula, a data frame with columns of the same names as the
variables used. A vector will be interpreted
as a row vector.  If \code{newdata} is missing, an attempt will be
made to retrieve the data used to fit the \code{lqs} object.
}}
\value{
A vector of predictions.
}
\details{
This function is a method for the generic function
\code{predict()} for class \code{lqs}.
It can be invoked by calling \code{predict(x)} for an
object \code{x} of the appropriate class, or directly by
calling \code{predict.lqs(x)} regardless of the
class of the object.

Missing values in \code{newdata} are handled by returning \code{NA} if the
linear discriminants cannot be evaluated. If \code{newdata} is omitted and
the \code{na.action} of the fit omitted cases, these will be omitted on the
prediction.
}
\author{B.D. Ripley}
\seealso{
\code{\link{lqs}}
}
\examples{
data(stackloss)
.Random.seed <- 1:4
fm <- lqs(stack.loss ~ ., data=stackloss, method="S", nsamp="exact")
predict(fm, stackloss)
}
\keyword{models}
% Converted by Sd2Rd version 0.3-2.