criteria.mocca: AIC, BIC, entropy for a functional clustering model

In fdaMocca: Model-Based Clustering for Functional Data with Covariates

AIC, BIC, entropy for a functional clustering model

Description

Function to extract the information criteria AIC and BIC, as well as the average Shannon entropy over all functional objects, for a fitted functional clustering mocca. The Shannon entropy is computed over the posterior probability distribution of belonging to a specific cluster given the functional object (see Arnqvist and Sjöstedt de Luna, 2019, for further details).

Usage

  criteria.mocca(x)

Arguments

x	fitted model objects of class mocca as produced by mocca().

Value

A table with the AIC, BIC and Shannon entropy values of the fitted model.

Author(s)

Per Arnqvist

References

Arnqvist, P., and Sjöstedt de Luna, S. (2019). Model based functional clustering of varved lake sediments. arXiv preprint arXiv:1904.10265.

See Also

logLik.mocca, mocca

Examples

## see examples in mocca() 

fdaMocca documentation built on April 4, 2025, 1:02 a.m.