Characterizing Correlation Matrices that Admit a Clustered Factor Representation

Fiche du document

Auteurs

Date

10 août 2023

Discipline

Economies et finances

Type de document

Textes imprimés

Périmètre

Publications

Identifiant

2308.05895

Source

arXiv - économie

Collection

Organisation

Cornell University

Mots-clés Und

Economics - Econometrics Statistics - Methodology

Sujets proches En

Matrix algebra Algebra, Matrix Matrixes (Algebra) Cracovians (Mathematics) Pattern Model

Citer ce document

Chen Tong et al., « Characterizing Correlation Matrices that Admit a Clustered Factor Representation », arXiv - économie

Partage / Export

export

Résumé 0

The Clustered Factor (CF) model induces a block structure on the correlation matrix and is commonly used to parameterize correlation matrices. Our results reveal that the CF model imposes superfluous restrictions on the correlation matrix. This can be avoided by a different parametrization, involving the logarithmic transformation of the block correlation matrix.

document thumbnail