\name{predict.pcaRes}
\title{Predict values from PCA.}
\usage{predict.pcaRes(object, newdata, pcs=nP(object), pre=TRUE, post=TRUE,
    ...)}
\description{Predict data using PCA model}
\details{This function extracts the predict values from a pcaRes object for
the PCA methods SVD, Nipals, PPCA and BPCA.  Newdata is first
centered if the PCA model was and then scores (\eqn{T}) and data
(\eqn{X}) is 'predicted' according to :
\eqn{\hat{T}=X_{new}P}{That=XnewP}
\eqn{\hat{X}_{new}=\hat{T}P'}{Xhat=ThatP'}.  Missing values are
set to zero before matrix multiplication to achieve NIPALS like
treatment of missing values.}
\value{A list with the following components: \item{scores}{The
predicted scores} \item{x}{The predicted data}}
\alias{predict.pcaRes}
\keyword{multivariate}
\author{Henning Redestig}
\arguments{\item{object}{\code{pcaRes} the \code{pcaRes} object of interest.}
\item{newdata}{\code{matrix} new data with same number of columns
as the used to compute \code{object}.}
\item{pcs}{\code{numeric} The number of PC's to consider}
\item{pre}{pre-process \code{newdata} based on the pre-processing
chosen for the PCA model}
\item{post}{unpre-process the final data (add the center back etc)}
\item{...}{Not passed on anywhere, included for S3 consistency.}}
\examples{data(iris)
hidden <- sample(nrow(iris), 50)
pcIr <- pca(iris[-hidden,1:4])
pcFull <- pca(iris[,1:4])
irisHat <- predict(pcIr, iris[hidden,1:4])
cor(irisHat$scores[,1], scores(pcFull)[hidden,1])}