Dear all,
I didn't find any graphical solution in the package "mva" to plot
the
canonical scores from a CCA (canonical correlation analysis).
Does anybody knows how to plot or has anybody already programmed :
- the map of the canonical scores,
- the graph of the canonical weights,
- the correlation circle i.e. the canonical loadings ?
Thank you for help ...
Francois M.
Hello Fran?ois, A lot of multivariate analyses are available in the ade4 package... but not canonical correlation analysis. However, you can use the graphical functions of this library to plot the results from mva''s cancor: - s.arrow for plotting variables by arrows - s.label to plot individuals - s.corcircle for correlation circle. Hope this helps, Cheers>Dear all, > >I didn''t find any graphical solution in the package "mva" to plot the >canonical scores from a CCA (canonical correlation analysis). >Does anybody knows how to plot or has anybody already programmed : > - the map of the canonical scores, > - the graph of the canonical weights, > - the correlation circle i.e. the canonical loadings ? >Thank you for help ... > >Francois M. > >______________________________________________ >R-help at stat.math.ethz.ch mailing list >https://www.stat.math.ethz.ch/mailman/listinfo/r-help-- St?phane DRAY --------------------------------------------------------------- Biom?trie et Biologie ?volutive - Equipe "?cologie Statistique" Universite Lyon 1 - Bat 711 - 69622 Villeurbanne CEDEX - France Tel : 04 72 43 27 56 Fax : 04 78 89 27 19 04 72 43 27 57 E-mail : dray at biomserv.univ-lyon1.fr --------------------------------------------------------------- Web http://www.steph280.freesurf.fr/ ---------------------------------------------------------------
f.mercier at fournier.fr wrote:> Dear all, > > I didn''t find any graphical solution in the package "mva" to plot the > canonical scores from a CCA (canonical correlation analysis). > Does anybody knows how to plot or has anybody already programmed : > - the map of the canonical scores, > - the graph of the canonical weights, > - the correlation circle i.e. the canonical loadings ? > Thank you for help ... >Have a look at Jari Oksanen''s vegan package. It''s on CRAN, but it also has its own page: <http://cc.oulu.fi/~jarioksa/softhelp/vegan.html> Bob -- Bob O''Hara Rolf Nevanlinna Institute P.O. Box 4 (Yliopistonkatu 5) FIN-00014 University of Helsinki Finland Telephone: +358-9-191 23743 Mobile: +358 50 599 0540 Fax: +358-9-191 22 779 WWW: http://www.RNI.Helsinki.FI/~boh/
If the original poster actually meant output from cancor() in library(mva) then I don''t think Jari''s vegan package will necessarily work "out of the box" for objects created using cancor(). Quoting the help file on scores() : <quote> Currently the function seems to work at least for `isoMDS'', `prcomp'', `princomp'', `ca'', `pca''. It may work for other cases, or fail mysteriously. </quote> I''ve just looked at the code for scores() in vegan (which is used to plot non-vegan-created ordination results) and it does not know about the values returned in a cancor object (cor, xcoef, ycoef, xcenter, ycenter etc.). There has been confusion over the use of three letter acronyms for methods in community ecology with some people using CCA for canonical correlation analysis, and others, like Jari and in the limnology/ecology field, using CCA to mean Canonical Correspondence Analysis. The two methods are very different. (I prefer CCA = Canonical Correspondence Analysis myself - but that how I learned the method!) Hope this helps. Gav %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Gavin Simpson [T] +44 (0)20 7679 5522 ENSIS Research Fellow [F] +44 (0)20 7679 7565 ENSIS Ltd. & ECRC [E] gavin.simpson at ucl.ac.uk UCL Department of Geography [W] http://www.ucl.ac.uk/~ucfagls/cv/ 26 Bedford Way [W] http://www.ucl.ac.uk/~ucfagls/ London. WC1H 0AP. %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% -----Original Message----- From: r-help-bounces at stat.math.ethz.ch [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Anon. Sent: 28 March 2003 11:29 To: f.mercier at fournier.fr Cc: r-help at stat.math.ethz.ch Subject: Re: [R] Plot of Canonical Correlation Analysis f.mercier at fournier.fr wrote:> Dear all, > > I didn''t find any graphical solution in the package "mva" to plot the > canonical scores from a CCA (canonical correlation analysis). > Does anybody knows how to plot or has anybody already programmed : > - the map of the canonical scores, > - the graph of the canonical weights, > - the correlation circle i.e. the canonical loadings ? > Thank you for help ... >Have a look at Jari Oksanen''s vegan package. It''s on CRAN, but it also has its own page: <http://cc.oulu.fi/~jarioksa/softhelp/vegan.html> Bob -- Bob O''Hara Rolf Nevanlinna Institute P.O. Box 4 (Yliopistonkatu 5) FIN-00014 University of Helsinki Finland Telephone: +358-9-191 23743 Mobile: +358 50 599 0540 Fax: +358-9-191 22 779 WWW: http://www.RNI.Helsinki.FI/~boh/ ______________________________________________ R-help at stat.math.ethz.ch mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
On Fri, 2003-03-28 at 13:29, Anon. wrote:> f.mercier at fournier.fr wrote: > > Dear all, > > > > I didn''t find any graphical solution in the package "mva" to plot the > > canonical scores from a CCA (canonical correlation analysis). > > Does anybody knows how to plot or has anybody already programmed : > > - the map of the canonical scores, > > - the graph of the canonical weights, > > - the correlation circle i.e. the canonical loadings ? > > Thank you for help ... > > > Have a look at Jari Oksanen''s vegan package. It''s on CRAN, but it also > has its own page: <http://cc.oulu.fi/~jarioksa/softhelp/vegan.html>No, don''t do that. The package has a function called cca, but that''s different CCA than your CCA. The package wouldn''t help you with your problem. We are just running short of TLAs. cheers, jari oksanen -- Jari Oksanen <jarioksa at sun3.oulu.fi>
f.mercier at fournier.fr wrote: > Dear all, > > I didn''t find any graphical solution in the package "mva" to plot the > canonical scores from a CCA (canonical correlation analysis). > Does anybody knows how to plot or has anybody already programmed : > - the map of the canonical scores, > - the graph of the canonical weights, > - the correlation circle i.e. the canonical loadings ? > Thank you for help ... > You may find an answer in the package ADE4, on CRAN. It has lot of graphical representations and documents with examples can be found on the Lyon university site. For canonical correlation analysis, you will find them at : http://pbil.univ-lyon1.fr/R/cours/bsb.pdf It''s written in french, but that won''t be a problem for you ;-)