Package: PUGMM 0.1.0

PUGMM: Parsimonious Ultrametric Gaussian Mixture Models

Finite Gaussian mixture models with parsimonious extended ultrametric covariance structures estimated via a grouped coordinate ascent algorithm, which is equivalent to the Expectation-Maximization algorithm. The thirteen ultrametric covariance structures implemented allow for the inspection of different hierarchical relationships among variables. The estimation of an ultrametric correlation matrix is included as a function. The methodologies are described in Cavicchia, Vichi, Zaccaria (2024) <doi:10.1007/s11222-024-10405-9>, Cavicchia, Vichi, Zaccaria (2022) <doi:10.1007/s11634-021-00488-x> and Cavicchia, Vichi, Zaccaria (2020) <doi:10.1007/s11634-020-00400-z>.

Authors:Giorgia Zaccaria [aut, cre], Carlo Cavicchia [aut], Lorenzo Balzotti [aut]