One-Sided Confidence Intervals for Means of Positively Skewed Distributions

Xiao Hua Zhou, Sujuan Gao

Research output: Contribution to journalArticlepeer-review

23 Scopus citations

Abstract

In this article, we study the coverage accuracy of one-sided confidence intervals based on Hall’s and Johnson’s transformation methods and their bootstrap versions for means of positively skewed distributions. We confirm Hall’s finding that a lower endpoint confidence interval based on his transformation method provides better coverage accuracy than Johnson’s transformation method. We also find that Hall’s upper endpoint confidence interval has poor coverage accuracy. Furthermore, we find that the bootstrap method, based on Hall’s transformation, yields the best coverage accuracy for both upper and lower endpoint confidence intervals.

Original languageEnglish (US)
Pages (from-to)100-104
Number of pages5
JournalAmerican Statistician
Volume54
Issue number2
DOIs
StatePublished - May 2000

Keywords

  • Bootstrap
  • Edgeworth expansion
  • ML estimators
  • Occupational exposures
  • Skewness

ASJC Scopus subject areas

  • Statistics and Probability
  • Mathematics(all)
  • Statistics, Probability and Uncertainty

Fingerprint Dive into the research topics of 'One-Sided Confidence Intervals for Means of Positively Skewed Distributions'. Together they form a unique fingerprint.

Cite this