The efficiency factorization multiplier for the Watson efficiency in partitioned linear models: Some examples and a literature review

Ka Lok Chu, Jarkko Isotalo, Simo Puntanen, George P. H. Styan

Research output: Contribution to journalArticleScientificpeer-review

2 Citations (Scopus)

Abstract

We consider partitioned linear models where the model matrix X = (X-1 : X-2) has full column rank, and concent rate on the special case where X-1 ' X-2 = 0 when we say that the model is orthogonally partitioned. We assume that the underlying covariance, matrix is positive definite and introduce the efficiency factorization multiplier which relates the total Watson efficiency of ordinary least squares to the product of the two subset Watson efficiencies. We illustrate our findings with several examples and present a literature review. (C) 2007 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)3336-3351
Number of pages16
JournalJournal of Statistical Planning and Inference
Volume137
Issue number11
DOIs
Publication statusPublished - 1 Nov 2007
Externally publishedYes
Publication typeA1 Journal article-refereed
Event14th International Workshop on Matrices and Statistics - Auckland, New Zealand
Duration: 29 Mar 20051 Apr 2005

Keywords

  • best linear unbiased estimation
  • Bloom field-Watson-Knott inequality
  • BLUE
  • efficiency factorization multiplier
  • Gauss-Markov model
  • generalized efficiency function
  • Geoffrey Stuart Watson (1921-1998)
  • OLSE
  • ordinary least squares estimation
  • partitioned linear models
  • splitting the efficiency
  • total Watson efficiency
  • Watson efficiency
  • ORDINARY LEAST-SQUARES
  • SERIAL-CORRELATION
  • INEFFICIENCY

Fingerprint

Dive into the research topics of 'The efficiency factorization multiplier for the Watson efficiency in partitioned linear models: Some examples and a literature review'. Together they form a unique fingerprint.

Cite this