The ultrametric correlation matrix for modelling hierarchical latent concepts

Carlo Cavicchia, Maurizio Vichi, Giorgia Zaccaria*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

5 Citations (Scopus)

Abstract

Many relevant multidimensional phenomena are defined by nested latent concepts,
which can be represented by a tree-structure supposing a hierarchical relationship
among manifest variables. The root of the tree is a general concept which includes
more specific ones. The aim of the paper is to reconstruct an observed data correlation
matrix of manifest variables through an ultrametric correlation matrix which is able to
pinpoint the hierarchical nature of the phenomenon under study. With this scope, we
introduce a novel model which detects consistent latent concepts and their relationships
starting from the observed correlation matrix
Original languageEnglish
Pages (from-to)837-853
JournalAdvances in Data Analysis and Classification
Volume14
Issue number4
DOIs
Publication statusPublished - 28 May 2020
Externally publishedYes

Bibliographical note

Not EUR

Fingerprint

Dive into the research topics of 'The ultrametric correlation matrix for modelling hierarchical latent concepts'. Together they form a unique fingerprint.

Cite this