A mixed estimator interpretation of ridge regression

Vernon L. Greene

Research output: Contribution to journalArticle

Abstract

It is shown that a formal isomorphism between the ridge estimator and the homogeneous case of the Theil-Goldberger mixed estimator leads to a general interpretation of ridge regression as ordinary least squares estimation subject to a prior stochastic constraint that all slope coefficients in the model are zero. Users of ridge regression are cautioned to consider this implied specification in their use and interpretation of the technique.

Original languageEnglish (US)
Pages (from-to)297-300
Number of pages4
JournalSocial Science Research
Volume11
Issue number3
DOIs
StatePublished - Sep 1982

ASJC Scopus subject areas

  • Education
  • Sociology and Political Science

Fingerprint Dive into the research topics of 'A mixed estimator interpretation of ridge regression'. Together they form a unique fingerprint.

  • Cite this