Followup: Re: [R] Interaction Plots in R

Jonathan Baron baron at cattell.psych.upenn.edu
Wed May 24 17:59:03 CEST 2000


It would be nice to be able to do quickly and easily what
are called "parallel coordinate plots" in Systat.  This
was the feature that kept me using Systat for years and
years.  If you have an experimental design with several
variables for each of several subjects, the plot consists
of one like per subject.  The variables are listed along
the horizontal axis.  Patterns in the data just leap out.
Not only differences between variables but also clusters
of subjects, correlations, etc.

Now this CAN be done NOW in R.  I've done it.  I have,
somewhere, the code to produce it, which was based on
what Prof. Ripley gave me (I think) in response to an
earlier post.  In order to do it, though, I had to
transform the data from its original layout (one row per
subject) to a different one (one row per observation).
Often this is necessary anyway (even in Systat), so it
isn't a BIG bother.  But it would be NICE to be able to
look at a parallel plot right away, before trying anything
else.

On the other hand, I worry a little that, if all requests
like this one found their way into the next version or a
later one, it would become bloated and slow (like recent
versions of Systat, compared to older ones :) ).  So don't
take me too seriously!

Jon Baron
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._



More information about the R-help mailing list