[R] MANOVA, SCC and multiple comparisons

Frédéric Chiroleu frederic.chiroleu at cirad.fr
Mon Mar 31 09:07:39 CEST 2008


Bonjour,

we wanted to fit a manova as descripted in Marieta /et al./ 2003, 
"convergent habitat segregation of /Aedes aegyptii/ and /Aedes 
albopictus/ (Diptera: /Culicidae/) in Southern Brazil and Florida", /J. 
Med. Entomol./, *40* (6), 785-794. They did their analysis with SAS 
software.
We have the same kind of data with two insect species and city, habitat 
and season factors. We used the function manova() and it was OK for 
multivariate analysis. We have two questions (we have searched, with the 
help tools we know, on the site and on many packages without success ) :

1/ The next step of our analysis was to calculate the Standardized 
Canonical Coefficients (SCC); we have no idea of how to do. Is there 
some link with a PCA on Instrumental Variables ? The explaination in the 
article was not clear for us.

2/ As in a ANOVA, we wanted to realize mean comparisons. Marieta et al. 
used bivariate pairwise contrasts of a factor within each level of the 
other factor (for significant interactions) using Dunn-Sidak method and 
univariate contrasts of pairs of main effects (for significant main 
effects) using Dunn-Sidak method. We tried to use the glht() function 
(from multcomp package) without success because of the nature of 
manova() object. Has someone an helpful advice to give ?

Merci beaucoup, (Thanks a lot)

Bien cordialement, (Sincerely yours)

Frédéric. 
-- 
Dr. Frédéric Chiroleu
Biométricien
CIRAD-Systèmes Biologiques (Cirad-Bios)
UMR 53 PVBMT (Peuplements Végétaux et Bio-agresseurs en Milieu Tropical)
Laboratoire d'Ecologie Terrestre et de Lutte Intégrée (LETLI)
Pôle de Protection des Plantes (3P)
7, chemin de l'IRAT - Ligne Paradis
97410 Saint-Pierre
Île de la Réunion - France
Tél. : +262 (0)262 499 230
Standard : +262 (0)262 499 200
Fax : +262 (0)262 499 293
Courriel : frederic.chiroleu at cirad.fr



More information about the R-help mailing list