Univariate and multivariate outlier identification for skewed or heavy-tailed distributions

Vincenzo Verardi, Catherine Vermandele

Research output: Contribution to journalArticlepeer-review

Abstract

In univariate and in multivariate analyses, it is difficult to identify outliers in the case of skewed or heavy-tailed distributions. In this article, we propose simple univariate and multivariate outlier identification procedures that perform well with these types of distributions while keeping the computational complexity low. We describe the commands gboxplot (univariate case) and sdasym (multivariate case), which implement these procedures in Stata.

Original languageEnglish
Article numberst0533
Pages (from-to)517-532
Number of pages16
JournalStata Journal
Volume18
Issue number3
DOIs
Publication statusPublished - Sep 2018

Keywords

  • Box plot
  • Gboxplot
  • Generalized box plot
  • Outlier detection
  • Outlyingness
  • Projection
  • Sdasym
  • St0533
  • Tukey g-and-h distribution

Fingerprint Dive into the research topics of 'Univariate and multivariate outlier identification for skewed or heavy-tailed distributions'. Together they form a unique fingerprint.

Cite this