Hello Sara,
I am not sure that ktab analysis is suited to your situation.
In your case, you have :
- one reference table ( species data)
- three environmental tables
I think it would be better to use concordance analysis (k+1) whish is
devoted to study the common variations of k tables relatively to the
structure of a reference table.
If you have
Spe: table with sites as rows and species as columns
Mil: table with environemental variables as row and sites as column
Perform COA on Spe
Use Ktabutil (Kinit) and normalize the rows of mil (i.e. variables) with
the sites weights of Correspondence analysis (Spe.fcpl) as column weights.
Then, use K+1 to match the correpondence analysis to the ktab.
Hope this helps,
Could you please tell me if you find interesting results,
Sincerely.
At 06:10 15/03/2004, Your Name wrote:
>Dear all,
>
>After studying and trying many possible analysis, I have concluded that
>the MFA-AFMULT is an apropriate method to show us the relationship and
>importance of many measured environmental variables.
>
>I have 3 diferent types of environmental variables: soil data,
>vegetational data, topographic data. So I have considered a kTab with
>this 3 groups/blocs.
>
>Now I need to relate all that to the Species data!
>
>What and how should I do that?
>
>I have also done the MFA-AFMULT for a kTab including also the species
>data (as bloc 4)!
>The results are Ok from the point of view of ecological
>knowledge/interpretation/excpected results!
>
>But this obligates me to perform PCA on the species data and I am
>affraid that departing from a CoA should be more correct to these
>data...
>
>Hope you can advise me on this.
>
>Best regards,
>Sara Mouro.
>--
Stéphane DRAY
--------------------------------------------------------------------------------------------------
Département des Sciences Biologiques
Université de Montréal, C.P. 6128, succursale centre-ville
Montréal, Québec H3C 3J7, Canada
Tel : 514 343 6111 poste 1233
E-mail : stephane.dray@umontreal.ca
--------------------------------------------------------------------------------------------------
Web http://www.steph280.freesurf.fr/
--------------------------------------------------------------------------------------------------
This archive was generated by hypermail 2b30 : Tue Sep 07 2004 - 13:30:56 MEST