Zonation of sequences of heteroscedastic multivariate data

Douglas M. Hawkins, J. A. Ten Krooden

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


A problem in the earth sciences is to reduce a sequence of observation vectors X1, X2, ..., XN to a set of internally homogeneous segments or zones. This paper uses the model that the observation vectors in the ith zone are a random sample from the multivariate normal N(ξi, Σi) distribution. It is demonstrated that the maximum likelihood estimates of the boundaries between zones may be determined by dynamic programming, and a FORTRAN algorithm to perform this estimation is given.

Original languageEnglish (US)
Pages (from-to)189-194
Number of pages6
JournalComputers and Geosciences
Issue number2
StatePublished - 1979
Externally publishedYes


  • Dynamic programming
  • Heteroscedastic model
  • Homoscedastic model
  • Maximum likelihood estimates
  • Principal components


Dive into the research topics of 'Zonation of sequences of heteroscedastic multivariate data'. Together they form a unique fingerprint.

Cite this