Belatedly, a couple of corrections:
1. It seems that radar graphics and star graphics
are different. Crudely, radar seems to mean
stars superimposed. Or perhaps just one star.
2. Sorry for forgetting Scott's example code.
That unintentionally reinforces a point I made
in another thread about gems in the archives
that can get overlooked because they don't get
beyond postings into FAQs or published programs
or papers.
And a question: are these graphs really
effective? Using a bunch of radii to
represent a bunch of values is a clever way
to map from many dimensions to two, but
in practice I have a hard time reading off
any but the grossest contrasts. It's like
Chernoff faces all over again: clever, but
effective? Any experiences or arguments
to the contrary?
As some might guess, I much prefer parallel
coordinate plots for what I see as the same
problem.
Nick
[email protected]
[email protected]
> Thanks Scott, it was helpful. I had to edit the "do" file,
> but it worked.
> Thanks Nick for the interest.
>
[email protected]
> The example at:
>
> http://www.stata.com/statalist/archive/2005-07/msg00272.html
>
> may be helpful.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
