Conditioning Intervals
DESCRIPTION:
This function is used to create the conditioning intervals for a conditioning plot (coplot) and controls their number and the amount of overlap between intervals.
USAGE: 
co.intervals(x, number = 6, overlap = 0.5)
REQUIRED ARGUMENTS:
x:
data.
OPTIONAL ARGUMENTS:
number:
number of intervals. Default is 6
overlap:
fraction of points shared by two successive intervals. Default is 1/2.
VALUE:
a matrix with 2 columns and number rows. The left column contains the values of the left end points of the intervals, and the right collumn contains the corresponding right end points.
DETAILS:
The rows of the result, which are used as conditioning intervals in coplot, describe the endpoints of intervals that have the following properties: (1) the first interval has min(x) as its left endpoint and the last interval has max(x) as its right endpoint. (2) All other endpoints are values in x. (3) The numbers of values of x in the intervals are as nearly equal as possible. (4) For two successive intervals, the fraction of points shared by the intervals is as close to overlap as possible.
SEE ALSO:
coplot , panel.smooth .
EXAMPLES: 
E.intervals <- co.intervals(ethanol$E, 9, 0.25)
E.intervals


# produces the following output:
       [,1]  [,2]
 [1,] 0.535 0.686
 [2,] 0.655 0.761
 [3,] 0.733 0.811
 [4,] 0.808 0.899
 [5,] 0.892 1.002
 [6,] 0.990 1.045
 [7,] 1.042 1.125
 [8,] 1.115 1.189
 [9,] 1.175 1.232


# plot results
coplot(NOx ~ C | E, given.values = E.intervals, data = ethanol,
       panel = function(x,y) panel.smooth(x, y, span = 1,
       degree = 1))