Covariance reducing models: An alternative to spectral modelling of covariance matrices

R. Dennis Cook, Liliana Forzani

Research output: Contribution to journalArticle

12 Scopus citations

Abstract

We introduce covariance reducing models for studying the sample covariance matrices of a random vector observed in different populations. The models are based on reducing the sample covariance matrices to an informational core that is sufficient to characterize the variance heterogeneity among the populations. They possess useful equivariance properties and provide a clear alternative to spectral models for covariance matrices.

Original languageEnglish (US)
Pages (from-to)799-812
Number of pages14
JournalBiometrika
Volume95
Issue number4
DOIs
StatePublished - Dec 2008

Keywords

  • Central subspace
  • Dimension reduction
  • Envelopes
  • Grassmann manifolds
  • Reducing subspaces

Fingerprint Dive into the research topics of 'Covariance reducing models: An alternative to spectral modelling of covariance matrices'. Together they form a unique fingerprint.

  • Cite this