Using a nonparametric bootstrap to obtain a confidence interval for pearson's r with cluster randomized data: A case study

David A. Wagstaff, Elvira Elek, Stephen Kulis, Flavio Marsiglia

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

A nonparametric bootstrap was used to obtain an interval estimate of Pearson's r, and test the null hypothesis that there was no association between 5th grade students' positive substance use expectancies and their intentions to not use substances. The students were participating in a substance use prevention program in which the unit of randomization was a public middle school. The bootstrap estimate indicated that expectancies explained 21% of the variability in students' intentions (r = 0.46, 95% CI = [0.40, 0.50]). This case study illustrates the use of a nonparametric bootstrap with cluster randomized data and the danger posed if outliers are not identified and addressed. Editors' Strategic Implications: Prevention researchers will benefit from the authors' detailed description of this nonparametric bootstrap approach for cluster randomized data and their thoughtful discussion of the potential impact of cluster sizes and outliers.

Original languageEnglish (US)
Pages (from-to)497-512
Number of pages16
JournalJournal of Primary Prevention
Volume30
Issue number5
DOIs
StatePublished - Sep 2009

Fingerprint

Confidence Intervals
Students
Random Allocation
Research Personnel

Keywords

  • Cluster randomization
  • Confidence interval
  • Nonparametric bootstrap
  • Pearson's r

ASJC Scopus subject areas

  • Public Health, Environmental and Occupational Health

Cite this

Using a nonparametric bootstrap to obtain a confidence interval for pearson's r with cluster randomized data : A case study. / Wagstaff, David A.; Elek, Elvira; Kulis, Stephen; Marsiglia, Flavio.

In: Journal of Primary Prevention, Vol. 30, No. 5, 09.2009, p. 497-512.

Research output: Contribution to journalArticle

@article{83332e2b0b2042ac9b69a7b8257d75bb,
title = "Using a nonparametric bootstrap to obtain a confidence interval for pearson's r with cluster randomized data: A case study",
abstract = "A nonparametric bootstrap was used to obtain an interval estimate of Pearson's r, and test the null hypothesis that there was no association between 5th grade students' positive substance use expectancies and their intentions to not use substances. The students were participating in a substance use prevention program in which the unit of randomization was a public middle school. The bootstrap estimate indicated that expectancies explained 21{\%} of the variability in students' intentions (r = 0.46, 95{\%} CI = [0.40, 0.50]). This case study illustrates the use of a nonparametric bootstrap with cluster randomized data and the danger posed if outliers are not identified and addressed. Editors' Strategic Implications: Prevention researchers will benefit from the authors' detailed description of this nonparametric bootstrap approach for cluster randomized data and their thoughtful discussion of the potential impact of cluster sizes and outliers.",
keywords = "Cluster randomization, Confidence interval, Nonparametric bootstrap, Pearson's r",
author = "Wagstaff, {David A.} and Elvira Elek and Stephen Kulis and Flavio Marsiglia",
year = "2009",
month = "9",
doi = "10.1007/s10935-009-0191-y",
language = "English (US)",
volume = "30",
pages = "497--512",
journal = "Journal of Primary Prevention",
issn = "0278-095X",
publisher = "Kluwer Academic/Human Sciences Press Inc.",
number = "5",

}

TY - JOUR

T1 - Using a nonparametric bootstrap to obtain a confidence interval for pearson's r with cluster randomized data

T2 - A case study

AU - Wagstaff, David A.

AU - Elek, Elvira

AU - Kulis, Stephen

AU - Marsiglia, Flavio

PY - 2009/9

Y1 - 2009/9

N2 - A nonparametric bootstrap was used to obtain an interval estimate of Pearson's r, and test the null hypothesis that there was no association between 5th grade students' positive substance use expectancies and their intentions to not use substances. The students were participating in a substance use prevention program in which the unit of randomization was a public middle school. The bootstrap estimate indicated that expectancies explained 21% of the variability in students' intentions (r = 0.46, 95% CI = [0.40, 0.50]). This case study illustrates the use of a nonparametric bootstrap with cluster randomized data and the danger posed if outliers are not identified and addressed. Editors' Strategic Implications: Prevention researchers will benefit from the authors' detailed description of this nonparametric bootstrap approach for cluster randomized data and their thoughtful discussion of the potential impact of cluster sizes and outliers.

AB - A nonparametric bootstrap was used to obtain an interval estimate of Pearson's r, and test the null hypothesis that there was no association between 5th grade students' positive substance use expectancies and their intentions to not use substances. The students were participating in a substance use prevention program in which the unit of randomization was a public middle school. The bootstrap estimate indicated that expectancies explained 21% of the variability in students' intentions (r = 0.46, 95% CI = [0.40, 0.50]). This case study illustrates the use of a nonparametric bootstrap with cluster randomized data and the danger posed if outliers are not identified and addressed. Editors' Strategic Implications: Prevention researchers will benefit from the authors' detailed description of this nonparametric bootstrap approach for cluster randomized data and their thoughtful discussion of the potential impact of cluster sizes and outliers.

KW - Cluster randomization

KW - Confidence interval

KW - Nonparametric bootstrap

KW - Pearson's r

UR - http://www.scopus.com/inward/record.url?scp=69249182578&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69249182578&partnerID=8YFLogxK

U2 - 10.1007/s10935-009-0191-y

DO - 10.1007/s10935-009-0191-y

M3 - Article

C2 - 19685290

AN - SCOPUS:69249182578

VL - 30

SP - 497

EP - 512

JO - Journal of Primary Prevention

JF - Journal of Primary Prevention

SN - 0278-095X

IS - 5

ER -