Display Local Regression Surface
DESCRIPTION:
Produces a local regression surface on the current graphics device.
USAGE: 
plot.preplot.loess(object, xlab = object$xlab, ylab = object$ylab,
                   which.plots = object$which.plots, rows, columns,
                   show.given = TRUE, ...)
REQUIRED ARGUMENTS:
object:
a preplot.loess object which is created by the function preplot.loess() when the user wishes to save the evaluations of the surface that are carried out to make the coplot.
OPTIONAL ARGUMENTS:
xlab:
character vector of labels for predictors. If the elements have names, they are matched to the names in formula; if not, the elements are assigned, in order, according to the order in which the predictors appear in formula.
ylab:
a label for the response.
which.plots:
a character vector of names of predictors that determines the coplots that are made.
rows:
for the case of one given predictor, the number of rows of the matrix of dependence panels. If missing, the following is the default: let k be the number of given values; if columns is missing, then rows <- ceiling(sqrt(k)), else rows <- ceiling(k/columns). This argument is not used if there are two given predictors.
columns:
for the case of one given predictor, the number of columns of the matrix of dependence panels. If missing, the following is the default: let k be the number of given values; if rows is missing, columns <- ceiling(k/ceiling(sqrt(k))), else columns <- ceiling(k/rows). This argument is not used if there are two given predictors.
show.given:
if FALSE, given panels are not included.

Graphical parameters may also be supplied as arguments to this function (see par).

SIDE EFFECTS:
a plot is produced on the current graphics device.
DETAILS:
This function is a method for the generic function plot for class "preplot.loess". It can be invoked by calling plot for an object of the appropriate class, or directly by calling plot.preplot.loess regardless of the class of the object.

This function graphs the fitted surface of a local regression model for one, two or three predictors. For one predictor, a curve is graphed against the predictor. For two or three predictors, a coplot is made against each predictor, conditional on the others. Each dependence panel of a coplot shows a curve that is a slice through the surface and is based on an evaluation for evaluaton equally-spaced values of the predictor ranging between values specified by ranges; in addition, confidence intervals at confidence equally-spaced values over the same range are shown. These arguments are specified during the creation of the preplot object by preplot.loess(). Normally, the user will want to make all coplots, but coplots against just certain predictors can be made by using the argument which.plots.

SEE ALSO:
anova.loess , loess , loess.control , predict.loess , pointwise , preplot.loess , specs.loess .
EXAMPLES: 
air.m <- loess(ozone ~ radiation, data = air)
air.m.pp <- preplot(air.m, given = 5, confidence = 7)
plot(air.m.pp, which.plots = "radiation")