| dudi.rwcoa {made4} | R Documentation |
dudi.rwcoa Row weighted COA, calls forrwcoa to perform row
weighted correspondence analysis.
dudi.rwcoa(df, rowweights = rep(1/nrow(df),nrow(df)), ...)
df |
a data.frame containing positive or null values. It should not
contain missing (NA) values. |
rowweights |
a vector of row weights (by default, uniform row weights) |
... |
further arguments passed to or from other methods ) |
Performs row weighted COA. Calls forrwcoa to calculates weights.
Returns a list of class 'coa', 'rwcoa', and 'dudi' (see dudi)
In the paper by Culhane et al., 2002, coinertia analysis
was performed with two COAs, a standard COA and a row weighted COA dudi.rwcoa, on
the two gene expression datasets. However it is now recommended to perform
two non-symmetric COA, instead of two COA. This avoids having to force
the row weights from one analysis on the second. To perform
non-symmetric correspondence coinertia analysis, use nsc.coinertia.
Aedin Culhane, A.B. Dufour
Culhane AC, et al., 2003 Cross platform comparison and visualisation of gene expression data using co-inertia analysis. BMC Bioinformatics. 4:59
See Also as
dudi,dudi.coa,dudi.pca
nsc.coinertia
if (require(ade4, quiet = TRUE)) {
data(atlas)
coa1=dudi.coa(atlas$birds,scannf=FALSE)
coa2=dudi.coa(forrwcoa(atlas$birds),scannf=FALSE)
coa3=dudi.rwcoa(atlas$birds, rowweights=coa1$lw, scannf=FALSE)
}