I am interested in the selecting the optimal number of principal components in functional principal component analysis (FPCA). There are various techniques to do that for example AIC, BIC etc. (I am not much familiar with all of those). One of them is to choose this parameter in such a way that 84% variance is explained. This can be done in R-package fda
using pca.fd(fdobj, nharm = .......)
Here least value of nharm
is selected such that sum of variation proportion which is calculated by varprop
is just greater than or equal to 0.84. I have less knowledge about other methods. I have also gone through this link. But it does not serve my objective.
Your suggestions would be very helpful in this direction. I would happy to use R
for this problem.