[rkward-devel] New plugin and functions

Thomas Friedrichsmeier thomas.friedrichsmeier at ruhr-uni-bochum.de
Wed Apr 25 14:19:16 UTC 2007


Hi,

On Thursday 19 April 2007, I. Soumpasis wrote:
> The way I thought to implement all three parts (using "dependent" and
>
> "independent" variables) is something like this pseudocode:
> for (i=0; i<length(independents), ++i){
> table (dependent, independents[i])
> barplot (table (dependent, independent[i]))
> chisq.test (dependent, independent[i])
> }
>
> I do not know how doable is this. I also do not know if we can and how to
> count the number of the "independent" variables. How do you see this idea?

ok, I see now. I think both modes have their merits. The one that simply does 
crosstabulation of all input variables (factors) as table (x, y, z) would do. 
And the way you propose, where the factors are crossed pairwise. In the long 
run, we'll likely want to have both. In the short term, whatever gets done 
first will be available, first.

I guess we may actually need two separate plugins for this: A "2 dimensional 
crosstabs" and an "n dimensional crosstab" plugin, as it's probably hard to 
unite both in a single (comprehensible) GUI. The first would follow your 
approach, the second would create a single table with as many dimensions as 
input variables. Only the first would really need chisq.test and barplot 
functionality. Do you want to go ahead with the first one?

However, both should probably also allow saving the results (in the first case 
as a list of tables, in the second case as a single table).

Regards
Thomas
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
URL: <http://mail.kde.org/pipermail/rkward-devel/attachments/20070425/1d718ba7/attachment.sig>


More information about the Rkward-devel mailing list