PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
June 1, 1974Journal of the American Statistical Association605 citations

Robust Tests for the Equality of Variances

View Full Paper
MBMorton B. BrownAFAlan B. Forsythe

Key Points

  • This research aims to identify more robust formulations of Levene's test for assessing the equality of variances during nonnormal conditions.
  • Alternative formulations of Levene's test statistics were developed and analyzed.
  • Comparative analysis included the unmodified Levene's statistic, a jackknife procedure, and a χ2 test by Layard.
  • Robustness was evaluated under nonnormality conditions.
  • Alternative formulations provided greater robustness under nonnormality compared to the traditional approaches.
  • The unmodified Levene's statistic and jackknife procedure showed less reliable results under nonnormality.
  • The alternative tests performed significantly better, indicating more accurate variance assessments.

Abstract

Abstract Alternative formulations of Levene's test statistic for equality of variances are found to be robust under nonnormality. These statistics use more robust estimators of central location in place of the mean. They are compared with the unmodified Levene's statistic, a jackknife procedure, and a χ2 test suggested by Layard which are all found to be less robust under nonnormality.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Brown et al. (1974) studied this question.

synapsesocial.com/papers/69d769125f9a1dad5349018fhttps://doi.org/10.2307/2285659
Ask AI
Helpful
Bookmark
Share
View Full Paper