Combined bootstrap and cross validation procedure to find optimal number of PLS components
bootnComp(X, y, R = 99, plotting = FALSE)
predictors as a matrix
response
number of bootstrap replicates
if TRUE, a diagnostic plot is drawn for each bootstrap replicate
Including other information in a list, the optimal number of components
Heavily used internally in function impRZilr.
impRZilr
# NOT RUN { ## we refer to impRZilr() # }
Run the code above in your browser using DataCamp Workspace