ANALYSIS OF CONSTRAINED ROBUST REGRESSION ESTIMATORS.

Research output: Contribution to journalArticle

6 Scopus citations

Abstract

Multicollinearity and nonnormal errors are problems often encountered in the application of linear regression. Estimators are proposed for dealing with the simultaneous occurrence of both multicollinearity and nonnormality. These estimators are developed by combining biased estimation techniques with certain robust criteria. An iteratively reweighted least-squares procedure is used to compute the estimates. The performance of the combined estimators is studied empirically through Monte Carlo experiments structured according to factorial designs. Some guidelines for the use of these combined estimators are given.

Original languageEnglish (US)
Pages (from-to)283-296
Number of pages14
JournalNaval research logistics quarterly
Volume31
Issue number2
DOIs
StatePublished - Jan 1 1984
Externally publishedYes

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)

Cite this