Either plot projected data (if number is specified) or histogram of projection indices over all random starts
# S3 method for PP3
plot(x, number, main, nbig = 10, colvec = 1, lab = NULL, ...)
PP3 object that you wish to plot.
If missing, then the plot information concerning all
of the project indices over all random starts
(using function ix3sizeplot
) or, if specified,
plots the projected data associated with the number
random start outcome (using function
pdataplot
.
Argument for main title.
If plotting information on all indices, this argument controls the number of the largest projection indices and their identification number.
If plotting the projected data, you can supply a vector of colour indices to colour each observation in the plot
As for colvec
, but permits a text label for each
observation.
Other arguments to supply to the plot.
No specific value.
This function can produce two types of plot. The first type, if
the number
argument is not supplied, produces a histogram
of projection index values (in black) and superimposes the
pseudo-index value density estimate, and median, upper quartile,
0.9 quantile and maximum values as vertical dotted lines.
If the number
argument is specified, it should be one of
the projection random start numbers and then the projected data
associated with that maximised projection index is plotted.
The points in the plot can be coloured (using colvec
) or
a text label supplied (using lab
) argument.
Friedman, J.H. and Tukey, J.W. (1974) A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput., 23, 881-890.
Jones, M.C. and Sibson, R. (1987) What is projection pursuit? (with discussion) J. R. Statist. Soc. A, 150, 1-36.
Nason, G. P. (1995) Three-dimensional projection pursuit. J. R. Statist. Soc. C, 44, 411-430.
Nason, G. P. (2001) Robust projection indices. J. R. Statist. Soc. B, 63, 551-567.
# NOT RUN {
#
# See example in help for \code{\link{PP3many}}
#
# }
Run the code above in your browser using DataLab