Detection of Influential Observation in Linear Regression

R. Dennis Cook

Research output: Contribution to journalArticlepeer-review

1827 Scopus citations

Abstract

A new measure based on confidence ellipsoids is developed for judging the contribution of each data point to the determination of the least squares estimate of the parameter vector in full rank linear regression models. It is shown that the measure combines information from the studentized residuals and the variances of the residuals and predicted values. Two examples are presented.

Original languageEnglish (US)
Pages (from-to)15-18
Number of pages4
JournalTechnometrics
Volume19
Issue number1
DOIs
StatePublished - Feb 1977

Keywords

  • Confidence ellipsoids
  • Influential observations
  • Outliers
  • Variances of residuals

Fingerprint

Dive into the research topics of 'Detection of Influential Observation in Linear Regression'. Together they form a unique fingerprint.

Cite this