clustering method

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

clustering method

vagua1@mailbox.gr
Hello r-helpers

I have a correlation matrix (either pearson or spearman) of 41 variables and i want to use it to construct a tree with agnes command (instead of using the distances). My problem is that at the height of the tree i see negative scaling also which is not desired. Is there any r-command that uses as a distance method the correlation estimates instead of distances (distances=dissimilarities, correlations=simmilarities) so that the height of the tree will be between 0 (zero) and 1 (one). Or simply, is there a way to transform the correlations in a proper way and to use the agnes command for example so that the height of the tree will be between 0 and 1?Thank you very much.


_____________________________________________________________________________________


http://domains.europlanet.gr Ôï üíïìÜ óáò óôï internet ìüíï ìå 10 Åõñþ.

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Reply | Threaded
Open this post in threaded view
|

Re: clustering method

Sean Davis



On 12/30/05 5:27 AM, "[hidden email]" <[hidden email]> wrote:

> Hello r-helpers
>
> I have a correlation matrix (either pearson or spearman) of 41 variables and i
> want to use it to construct a tree with agnes command (instead of using the
> distances). My problem is that at the height of the tree i see negative
> scaling also which is not desired. Is there any r-command that uses as a
> distance method the correlation estimates instead of distances
> (distances=dissimilarities, correlations=simmilarities) so that the height of
> the tree will be between 0 (zero) and 1 (one). Or simply, is there a way to
> transform the correlations in a proper way and to use the agnes command for
> example so that the height of the tree will be between 0 and 1?Thank you very
> much.

1-correlation?

Sean

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html