[Taxacom] software recommendation please

[Richard Jensen]

 From the sample shown below, the data will yield a non-metric 
similarity (notice the inequality of the similarity of B-C versus C-B). 
There are non-metric similarity measures, such as those of Kulczynski 
and Yule, that can be used as input for cluster analysis and non-metric 
multidimensional scaling. NTSYSpc (available from Exeter Software) 
provides these and a variety of other coefficients.

Cheers,

Dick J

Richard Jensen, Professor
Department of Biology
Saint Mary’s College
Notre Dame, IN 46556
Tel: 574-284-4674



Soowon Cho wrote:
> Dear members,
>
> A friend of mine asked me about how to group his microorgarnisms based on
> certain reactions among each others, but I am not familiar with such.  He
> said his data is like the following:
>     A   B   C   D  .....
> A  0   1    0    1
> B  1   0    0    0
> C  0   1    0    1
> D  1   0    0    0
> :
>
> For the above, A is responding to B and D only, B is responding to A only, C
> is responding to B and D only,.....etc.
> His data is with nearly a hundred OTUs and he wants to know which software
> is good to use for grouping them based on the result.
>
> My initial thought was about UPGMA or PCA, but I am not sure.  Could anyone
> tell me which method (software) is good to analyze this kind of data for
> grouping based on "similarity"(I guess)?
>
> Sincerely,
> _______________________________________________
> Taxacom mailing list
> Taxacom at mailman.nhm.ku.edu
> http://mailman.nhm.ku.edu/mailman/listinfo/taxacom
>