[R] understanding the parameters of 'spca' function of 'elasticnet' package

Adib Shafi adib.mist at gmail.com
Fri Jul 18 19:00:22 CEST 2014


Hi all,

i am trying to use the 'spca' function of 'elasticnet' package. But i am
confused with the parameter 'para'.

Basically the parameter 'para' depends on the parameter 'sparse'. If
sparse="penalty", para is a vector of 1-norm penalty parameters. If
sparse="varnum",  para defines the number of sparse loadings to be obtained.

As my understanding, if i use sparse="penalty" i have to set the amount
of variance for each component in a vector. But how could i know the
amount of variance in this case?

If i use sparse='varnum', i have to set the number of features i want to
extract from each component in a vector. But i dont have these numbers
even because i dont know how many key features are present in each
component.

Thanks



More information about the R-help mailing list