Dear all,
I am using the PLS package for PLSR analysis. And I have a basic question
about the standardize procedure, which I feel the PLS manual does not
explain clearly. I am hoping that I could get some help from the list.
>From the example in the "Standardization of Data Matrices"
section, I can
standardize X matrix and make prediction by using:
mod=plsr(y~stdize(X),ncomp=6,data=NIR[NIR$train,])
pred=predict(mod,newdata=NIR[!NIR$train,])
In the manual, it is commented that the prediction is "automatically
standardized". So I guess I won't need to standardize X matrix of the
test
set for the prediction.
However, what if I do not want a standardize model from the beginning?
Then my code would be like:
mod=plsr(y~X,ncomp=6,data=NIR[NIR$train,])
But the R code for the prediction should still be the same (please
correct me if any code is wrong):
pred=predict(mod,newdata=NIR[!NIR$train,])
Would this time the X matrix of the newdata be automatical standardized or
not?
I am so confused about the "automatically standardization". Please
share
some experience. Really appreciate your kind help!
Sincerely,
Jeny