[R] extracting significant response variables

adeela uaf adeela.uaf at gmail.com
Fri Jun 26 08:09:55 CEST 2015


Hi,
My experiment consist of factorial structure with 25 genotypes and 3
salinity levels ( 25 cross 3) each with 3 replications.  14 responses were
taken from the experiment and I applied MANOVA but I am applying
discriminant analysis to know which response variable has significant
impact on the separation of groups. I am doing the following:
MANOVA<-manova(cbind(RL,SL,RFW,SFW,RDW,SDW,R.S..DW.,LA,NL,Na,K,Ca)~geneotype*S.Level,data=data)
For discriminant analysis, I made a group of 1 genotype with one level of
Salinity level hence a total of 75 groups.
group<-paste("g", gl(75,3,length=225))
LDA<-lda(group~RL+SL+RFW+SFW+RDW+SDW+R.S..DW.+LA+NL+Na+K+Ca+K.Na+Ca.Na,data=Sdata)

Is it appropriate way? Moreover when I am plotting discriminant scores
means with the circle of radius r=z/sqrt(replication) but the graph doesn't
make any sense as the circles are too small too see.
Thanks,
Adeela
-------------- next part --------------
A non-text attachment was scrubbed...
Name: lda.pdf
Type: application/pdf
Size: 5835 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20150626/15ce5441/attachment.pdf>


More information about the R-help mailing list