Categorical Functional Data Analysis. The cfda R Package

Categorical functional data represented by paths of a stochastic jump process with continuous time and a finite set of states are considered. As an extension of the multiple correspondence analysis to an infinite set of variables, optimal encodings of states over time are approximated using an arbitrary finite basis of functions. This allows dimension reduction, optimal representation, and visualisation of data in lower dimensional spaces. The methodology is implemented in the cfda R package and is illustrated using a real data set in the clustering framework.

Automated summary

This paper discusses categorical functional data represented by paths of a stochastic jump process and extends the concept of multiple correspondence analysis. By approximating the optimal encoding of states over time, it achieves dimension reduction, optimal representation, and visualization of data. The methodology is implemented in the cfda R package and demonstrated using a real data set in the clustering framework.