On the accuracy of bonferroni significance levels for detecting outliers in linear models

R. Dennis Cook, P. Prescott

Research output: Contribution to journalArticlepeer-review

23 Scopus citations

Abstract

At present, the first-order Bonferroni upper bound is the only practically useful tool for determining approximate critical values or p values for the maximum absolute studentized residual as a criterion for detecting a single outlier in a linear model. Available methods for assessing the accuracy of this bound require numerical integration and are difficult to apply routinely. We present a relatively simple alternative method that can be applied to any linear model and is suitable for routine use. The application to analyses of 2m factorial experiments and regression models is illustrated with several examples.

Original languageEnglish (US)
Pages (from-to)59-63
Number of pages5
JournalTechnometrics
Volume23
Issue number1
DOIs
StatePublished - Feb 1981

Bibliographical note

Funding Information:
This work was undertaken while the first author was a Hartley Visiting Fellow at the University of Southampton and was supported in part by grant l-ROl-GM25587 from the National Institute of General Medical Science, U.S. Department of Health, Education and Welfare. The authors are grateful to the editor, associatee ditor, and the refereesf or many helpful suggestions.

Keywords

  • Bonferroni bounds
  • Factorial experiments
  • Maximum absolute studentized residual
  • Outliers
  • P values
  • Regression

Fingerprint Dive into the research topics of 'On the accuracy of bonferroni significance levels for detecting outliers in linear models'. Together they form a unique fingerprint.

Cite this