predict.mvr.rd

做主成分回归和偏最小二乘回归

%% $Id: predict.mvr.Rd 99 2006-10-04 10:54:35Z bhm $
\encoding{latin1}
\name{predict.mvr}
\alias{predict.mvr}
\title{Predict Method for PLSR and PCR}
\description{
  Prediction for mvr (PCR, PLSR) models.  New responses or scores are
  predicted using a fitted model and a new matrix of observations.
}
\usage{
\method{predict}{mvr}(object, newdata, ncomp = 1:object$ncomp, comps,
        type = c("response", "scores"), na.action = na.pass, \dots)
}
\arguments{
  \item{object}{an \code{mvr} object.  The fitted model}
  \item{newdata}{a data frame.  The new data.  If missing, the training
    data is used.}
  \item{ncomp, comps}{vector of positive integers.  The components to use in
    the prediction.  See below.}
  \item{type}{character.  Whether to predict scores or response values}
  \item{na.action}{function determining what should be done with missing
    values in \code{newdata}.  The default is to predict \code{NA}.  See
    \code{\link{na.omit}} for alternatives.}
  \item{\dots}{further arguments.  Currently not used}
}
\details{
  When \code{type} is \code{"response"} (default), predicted response
  values are returned.  If \code{comps} is missing (or is \code{NULL}),
  predictions for \code{length(ncomp)} models with \code{ncomp[1]}
  components, \code{ncomp[2]} components, etc., are returned.
  Otherwise, predictions for a single model with the exact components in
  \code{comps} are returned.  (Note that in both cases, the intercept is
  always included in the predictions.  It can be removed by subtracting
  the \code{Ymeans} component of the fitted model.)

  When \code{type} is \code{"scores"}, predicted score values are
  returned for the components given in \code{comps}.  If \code{comps} is
  missing or \code{NULL}, \code{ncomps} is used instead.

  It is also possible to supply a matrix instead of a data frame as
  \code{newdata}, which is then assumed to be the \eqn{X} data matrix.
  Note that the usual checks for the type of the data are then
  omitted.  Also note that this is
  \emph{only} possible with \code{predict}; it will not work in
  functions like \code{\link{predplot}}, \code{\link{RMSEP}} or
  \code{\link{R2}}, because they also need the response variable of the new
  data.
}
\value{
  When \code{type} is \code{"response"}, a three dimensional array of
  predicted response values is returned.  The dimensions correspond to
  the observations, the response variables and the model sizes,
  respectively.

  When \code{type} is \code{"scores"}, a score matrix is returned.
}
\note{
  A warning message like \samp{'newdata' had 10 rows but variable(s)
    found have 106 rows} means that not all variables were found in the
  \code{newdata} data frame.  This (usually) happens if the formula
  contains terms like \code{yarn$NIR}.  Do not use such terms; use the
  \code{data} argument instead.  See \code{\link{mvr}} for details.
 }
\author{Ron Wehrens and Bj鴕n-Helge Mevik}
\seealso{\code{\link{mvr}}, \code{\link{summary.mvr}},
  \code{\link{coef.mvr}}, \code{\link{plot.mvr}}}
\examples{
data(yarn)
nir.mvr <- mvr(density ~ NIR, ncomp = 5, data = yarn[yarn$train,])

## Predicted responses for models with 1, 2, 3 and 4 components
pred.resp <- predict(nir.mvr, ncomp = 1:4, newdata = yarn[!yarn$train,])

## Predicted responses for a single model with components 1, 2, 3, 4
predict(nir.mvr, comps = 1:4, newdata = yarn[!yarn$train,])

## Predicted scores
predict(nir.mvr, comps = 1:3, type = "scores", newdata = yarn[!yarn$train,])
}
\keyword{regression}
\keyword{multivariate}