Font Size: 

The sparse and smooth functional clustering (SaS-Funclust) method, developed in Centofanti et al. (2023), is presented for sparse clustering of functional data, i.e., to split a sample of curves into homogeneous groups while jointly detecting the most informative portions of the domain. SaS-Funclust relies on a functional adaptive pairwise fusion penalty and a roughness penalty. The former allows identifying the noninformative portion of the domain, whereas the latter improves the interpretability by imposing some degree of smoothing to the cluster means. The practical advantages of the SaS-Funclust method are illustrated through a real-data example in the analysis of the Berkeley growth study dataset. The SaS-Funclust method is implemented in the R package sasfunclust, available on CRAN.