Hi,
I'm using Mark Dettling's supclust package.
I have a typical numeric matrix x of explanatory variables (n cases, p
features, n<< p).
I have a numeric vector y of length n, containing a quantitative
response variable.
I am interested in grouping features in a way which is strongly
predictive of response y (like in PLS approach).
In paper describing Pelora it is said that Pelora can be easily adapted
to this case.
However it seems to me that no explicit indication is given in supclust
user manual.
Should I simply call
aa<- pelora(x_training,y) and than
predict(aa, x_test, type="probs") ?
Thank You in advance
rossana
[[alternative HTML version deleted]]
______________________________________________
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
