%% $Id: coefplot.Rd 148 2007-10-16 20:33:38Z bhm $\encoding{latin1}\name{coefplot}\alias{coefplot}\title{Plot Regression Coefficients of PLSR and PCR models}\description{  Function to plot the regression coefficients of an \code{mvr} object.}\usage{coefplot(object, ncomp = object$ncomp, comps, intercept = FALSE,         separate = FALSE, nCols, nRows, labels, type = "l",         lty = 1:nLines, lwd = NULL, pch = 1:nLines, cex = NULL,         col = 1:nLines, legendpos, xlab = "variable",         ylab = "regression coefficient", main, pretty.xlabels = TRUE,         xlim, \dots)}\arguments{  \item{object}{an \code{mvr} object.  The fitted model.}  \item{ncomp, comps}{vector of positive integers.  The components to    plot.  See \code{\link{coef.mvr}} for details.}  \item{separate}{logical.  If \code{TRUE}, coefficients for different model    sizes are blotted in separate plots.}  \item{intercept}{logical.  Whether coefficients for the intercept should    be plotted.  Ignored if \code{comps} is specified.  Defaults to    \code{FALSE}.  See \code{\link{coef.mvr}} for details.}  \item{nCols, nRows}{integer.  The number of coloumns and rows the    plots will be laid out in.  If not specified, \code{coefplot} tries    to be intelligent.}  \item{labels}{optional.  Alternative \eqn{x} axis labels.  See Details.}  \item{type}{character.  What type of plot to make.  Defaults to    \code{"l"} (lines).  Alternative types include \code{"p"} (points)    and \code{"b"} (both).  See \code{\link{plot}} for a complete list    of types.}  \item{lty}{vector of line types (recycled as neccessary).  Line types can be    specified as integers or character strings (see \code{\link{par}}    for the details).}  \item{lwd}{vector of positive numbers (recycled as neccessary), giving    the width of the lines.}  \item{pch}{plot character.  A character string or a vector of    single characters or integers (recycled as neccessary).  See    \code{\link{points}} for all alternatives.}  \item{cex}{numeric vector of character expansion sizes (recycled as    neccessary) for the plotted symbols.}  \item{col}{character or integer vector of colors for plotted lines and    symbols (recycled as neccessary).  See \code{\link{par}} for the details.}  \item{legendpos}{Legend position.  Optional.  Ignored if \code{separate} is    \code{TRUE}.  If present, a legend is drawn at the given position.    The position can be specified symbolically (e.g., \code{legendpos =      "topright"}).  This requires \R >= 2.1.0.  Alternatively, the    position can be specified explicitly (\code{legendpos = t(c(x,y))})    or interactively (\code{legendpos = \link{locator}()}).  This only    works well for plots of single-response models.}  \item{xlab,ylab}{titles for \eqn{x} and \eqn{y} axes.  Typically    character strings, but can be expressions (e.g.,    \code{expression(R^2)} or lists.  See \code{\link{title}} for details.}  \item{main}{optional main title for the plot.  See Details.}  \item{pretty.xlabels}{logical.  If \code{TRUE}, \code{coefplot}    tries to plot the \eqn{x} labels more nicely.  See Details.}  \item{xlim}{optional vector of length two, with the \eqn{x} limits of    the plot.}  \item{\dots}{Further arguments sent to the underlying plot functions.}}\details{  \code{coefplot} handles multiple responses by making one plot for each  response.  If \code{separate} is \code{TRUE}, separate plots are made  for each combination of model size and response.  The plots are laid  out in a rectangular fashion.  If \code{legendpos} is given, a legend is drawn at the given position  (unless \code{separate} is \code{TRUE}).  The argument \code{labels} can be a vector of labels or one of  \code{"names"} and \code{"numbers"}.  The labels are  used as \eqn{x} axis labels.  If \code{labels} is \code{"names"} or  \code{"numbers"}, the variable names are used as labels, the  difference being that with \code{"numbers"}, the variable names are  converted to numbers, if possible.  Variable names of the forms  \samp{"number"} or \samp{"number text"} (where the space is optional),  are handled.  The argument \code{main} can be used to specify the main title of the  plot.  It is handled in a non-standard way.  If there is only on (sub)  plot, \code{main} will be used as the main title of the plot.  If  there is \emph{more} than one (sub) plot, however, the presence of  \code{main} will produce a corresponding \sQuote{global} title on the  page.  Any graphical parametres, e.g., \code{cex.main}, supplied to  \code{coefplot} will only affect the \sQuote{ordinary} plot titles,  not the \sQuote{global} one.  Its appearance can be changed by setting  the parameters with \code{\link{par}}, which will affect \emph{both}  titles.  (To have different settings for the two titles, one can  override the \code{par} settings with arguments to \code{coefplot}.)  The argument \code{pretty.xlabels} is only used when \code{labels} is  specified.  If \code{TRUE} (default), the code tries  to use a \sQuote{pretty} selection of labels.  If \code{labels} is  \code{"numbers"}, it also uses the numerical values of the labels for  horisontal spacing.  If one has excluded parts of the spectral  region, one might therefore want to use \code{pretty.xlabels = FALSE}.  The function can also be called through the \code{mvr} plot method by  specifying \code{plottype = "coefficients"}.}\author{Ron Wehrens and Bj鴕n-Helge Mevik}\note{\code{\link{legend}} has many options.  If you want greater  control over the appearance of the legend, omit the \code{legendpos}  argument and call \code{legend} manually.  The handling of \code{labels} and \code{pretty.xlabels} is experimental.}\seealso{\code{\link{mvr}}, \code{\link{plot.mvr}}, \code{\link{coef.mvr}},  \code{\link{plot}}, \code{\link{legend}}}\examples{data(yarn)mod.nir <- plsr(density ~ NIR, ncomp = 8, data = yarn)\dontrun{coefplot(mod.nir, ncomp = 1:6)plot(mod.nir, plottype = "coefficients", ncomp = 1:6) # Equivalent to the previous## Plot with legend:coefplot(mod.nir, ncom = 1:6, legendpos = "bottomright")}data(oliveoil)mod.sens <- plsr(sensory ~ chemical, ncomp = 4, data = oliveoil)\dontrun{coefplot(mod.sens, ncomp = 2:4, separate = TRUE)}}\keyword{regression}\keyword{multivariate}\keyword{hplot}