Confidence intervals for dependent data

Equating non-overlap with statistical significance

David Afshartous, Richard A Preston

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

We revisit the problem of determining confidence interval widths for the comparison of means. For the independent two-sample (two-sided) case, Goldstein and Healy (1995) draw attention to the fact that comparisons based on 95% error bars are not very effective in assessing the statistical significance of the difference in means and derive the correct confidence interval for such a comparison. We provide an extension to Goldstein and Healy (1995) to account for the correlation structure and unequal variances. We use the results to develop rules of thumb for evaluating differences, in an exploratory manner, like Moses (1987) and Cumming (2009), from the independent case. We illustrate the method for the simple comparison of two means in a real data set, provide R code that may be easily implemented in practice, and discuss the extension of the method to other applied problems.

Original languageEnglish
Pages (from-to)2296-2305
Number of pages10
JournalComputational Statistics and Data Analysis
Volume54
Issue number10
DOIs
StatePublished - Oct 1 2010

Fingerprint

Dependent Data
Statistical Significance
Confidence interval
Correlation Structure
Unequal

Keywords

  • Crossover trial
  • Margin of error
  • Significance test
  • Type I error

ASJC Scopus subject areas

  • Computational Mathematics
  • Computational Theory and Mathematics
  • Statistics and Probability
  • Applied Mathematics

Cite this

Confidence intervals for dependent data : Equating non-overlap with statistical significance. / Afshartous, David; Preston, Richard A.

In: Computational Statistics and Data Analysis, Vol. 54, No. 10, 01.10.2010, p. 2296-2305.

Research output: Contribution to journalArticle

@article{1254f74ad08e442a8fa2680523a3d604,
title = "Confidence intervals for dependent data: Equating non-overlap with statistical significance",
abstract = "We revisit the problem of determining confidence interval widths for the comparison of means. For the independent two-sample (two-sided) case, Goldstein and Healy (1995) draw attention to the fact that comparisons based on 95{\%} error bars are not very effective in assessing the statistical significance of the difference in means and derive the correct confidence interval for such a comparison. We provide an extension to Goldstein and Healy (1995) to account for the correlation structure and unequal variances. We use the results to develop rules of thumb for evaluating differences, in an exploratory manner, like Moses (1987) and Cumming (2009), from the independent case. We illustrate the method for the simple comparison of two means in a real data set, provide R code that may be easily implemented in practice, and discuss the extension of the method to other applied problems.",
keywords = "Crossover trial, Margin of error, Significance test, Type I error",
author = "David Afshartous and Preston, {Richard A}",
year = "2010",
month = "10",
day = "1",
doi = "10.1016/j.csda.2010.04.011",
language = "English",
volume = "54",
pages = "2296--2305",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",
number = "10",

}

TY - JOUR

T1 - Confidence intervals for dependent data

T2 - Equating non-overlap with statistical significance

AU - Afshartous, David

AU - Preston, Richard A

PY - 2010/10/1

Y1 - 2010/10/1

N2 - We revisit the problem of determining confidence interval widths for the comparison of means. For the independent two-sample (two-sided) case, Goldstein and Healy (1995) draw attention to the fact that comparisons based on 95% error bars are not very effective in assessing the statistical significance of the difference in means and derive the correct confidence interval for such a comparison. We provide an extension to Goldstein and Healy (1995) to account for the correlation structure and unequal variances. We use the results to develop rules of thumb for evaluating differences, in an exploratory manner, like Moses (1987) and Cumming (2009), from the independent case. We illustrate the method for the simple comparison of two means in a real data set, provide R code that may be easily implemented in practice, and discuss the extension of the method to other applied problems.

AB - We revisit the problem of determining confidence interval widths for the comparison of means. For the independent two-sample (two-sided) case, Goldstein and Healy (1995) draw attention to the fact that comparisons based on 95% error bars are not very effective in assessing the statistical significance of the difference in means and derive the correct confidence interval for such a comparison. We provide an extension to Goldstein and Healy (1995) to account for the correlation structure and unequal variances. We use the results to develop rules of thumb for evaluating differences, in an exploratory manner, like Moses (1987) and Cumming (2009), from the independent case. We illustrate the method for the simple comparison of two means in a real data set, provide R code that may be easily implemented in practice, and discuss the extension of the method to other applied problems.

KW - Crossover trial

KW - Margin of error

KW - Significance test

KW - Type I error

UR - http://www.scopus.com/inward/record.url?scp=77955269139&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955269139&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2010.04.011

DO - 10.1016/j.csda.2010.04.011

M3 - Article

VL - 54

SP - 2296

EP - 2305

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 10

ER -