[rkward-devel] correlation plugin [was: another mac issue]

[Thomas Friedrichsmeier]

Hi,

On Thursday 22 December 2011, meik michalke wrote:
> Am Donnerstag, 22. Dezember 2011 10:53:18 schrieb Thomas Friedrichsmeier:
> > Perhaps it would make sense to split up the plugin after all?
> 
> that was actually my first idea, but then i thought it's perhaps a bit
> confusing to find what you want if there's still a "correlation matrix"
> plugin (as long as it's not labelled "(except polyserial)", but that would
> be odd ;-)).

not sure, whether that would really be a problem, as "polyserial" would be 
fairly visible in the "Correlation"-menu. Add cross-links on the plugin
help pages, and I think we should be fine.

> then, if we were to split things, i think it would be much clearer to offer
> product-moment vs. ranks, but that wouldn't change these dialog issues at
> all.

True. Of course we could also split into three categories:
- Product-moment
- All ranks
- Mixed interval / ordinal data (polyserial)

The first two would look fairly similar, of course.
 
> in the current plugin, an alternative could be to check
> the number of levels (after as.factor()) and consider only variables that
> remain below a sane threshold. that number could be made configurable in a
> spinbox. how about that?

Well, that would be an interesting alternative. But I would think that two 
separate varslots are still the safest, and clearest option, here. So, IMO 
that would make sense as an addition, but not as a replacement.

Either way, that means one or more additional UI-elements, and potentially 
additonal R code for the polyserial correlation. Add to that, the output 
format is not ideally suited for polyserial. The more I think about it, the 
more I believe polyserial should go into a separate plugin.

Regards
Thomas
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 198 bytes
Desc: This is a digitally signed message part.
URL: <http://mail.kde.org/pipermail/rkward-devel/attachments/20111222/eba5a044/attachment.sig>