Influential observations in linear regression

R. Dennis Cook

Research output: Contribution to journalArticlepeer-review

426 Scopus citations

Abstract

Characteristics of observations which cause them to be influential in a least squares analysis are investigated and related to residual variances, residual correlations, and the convex hull of the observed values of the independent variables. It is shown how deleting an observation can substantially alter an analysis by changing the partial F-tests, the studentized residuals, the residual variances, the convex hull of the independent variables, and the estimated parameter vector. Outliers are discussed briefly, and an example is presented. © 1979, Taylor & Francis Group, LLC.

Original languageEnglish (US)
Pages (from-to)169-174
Number of pages6
JournalJournal of the American Statistical Association
Volume74
Issue number365
DOIs
StatePublished - 1979

Keywords

  • Deleting observations
  • Outliers
  • Partial F-tests
  • Residual correlations
  • Studentized residuals

Fingerprint

Dive into the research topics of 'Influential observations in linear regression'. Together they form a unique fingerprint.

Cite this