.BG
.FN pairs
.TL
Produce All Pair-wise Scatterplots
.CS
pairs(x, labels, type="p", head,
      full=FALSE, max, text, dataex)
.AG x
matrix of data to be plotted.
A scatter plot will be produced for each pair of
columns of `x'.
.NA
.AG labels
optional character vector for labelling the x and y axes of
the plots.  The strings `labels[1]', `labels[2]', etc. are
the labels for the 1st, 2nd, etc.  columns of `x'.
If supplied, the label
vector must have length equal to `ncol(x)'.
If `x' has a `dimnames' attribute, the default labels are the
column labels; otherwise, the
default labels are "Var 1", "Var 2", etc.  
.AG type
optional character string to define the type of the scatter
plot.  Possible values are "p", "l", "b" for points, lines
or both.  See also `text' below.
.AG head
optional character string for a running head.  This is
plotted as a title at the top of each page.  By default, the
name of the data is used.  If there is more than one page,
the page number is included in the title.
.AG full
should the full `ncol(x)-1' by `ncol(x)-1' array of plots be
produced?  By default, only the lower triangle is
produced, saving space and plot time, but making
interpretation harder.
.AG max
optional, suggested limit for the number of rows or columns
of plots on a single page.  Default forces all plots on 1
page.  The algorithm tries to choose an array of plots which
efficiently uses the available space on the display.
.AG text
optional vector of text to be plotted at each of the points.
If the length of the vector is less than `nrow(x)', elements
will be reused cyclically. If missing, the plotting is
controlled by `type'.
.AG dataex
character size for the plotted data points.
Default is the current value of parameter `cex'.
.GR
.EX
pairs(longley.x,head="Longley Data")
.PI 3.5i
.KW multivariate
.KW hplot
.WR
