The canonical decomposition of bivariate distributions

P. L. Chesson

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


The ordinary notion of a bivariate distribution has a natural generalisation. For this generalisation it is shown that a bivariate distribution can be characterised by a Hilbert space H and a family Mp, 0 ≤ p ≤ 1, of subspaces of H. H specifies the marginal distributions whilst Mp is a summary of the dependence structure. This characterisation extends existing ideas on canonical correlation.

Original languageEnglish (US)
Pages (from-to)526-537
Number of pages12
JournalJournal of Multivariate Analysis
Issue number4
StatePublished - Dec 1976


  • Bivariate distribution
  • Canonical correlation
  • Spectral theorem

ASJC Scopus subject areas

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty


Dive into the research topics of 'The canonical decomposition of bivariate distributions'. Together they form a unique fingerprint.

Cite this