Statistical power and sample size requirements for three level hierarchical cluster randomized trials

Moonseong Heo, Andrew C. Leon

Research output: Contribution to journalArticle

45 Citations (Scopus)

Abstract

Cluster randomized clinical trials (cluster-RCT), where the community entities serve as clusters, often yield data with three hierarchy levels. For example, interventions are randomly assigned to the clusters (level three unit). Health care professionals (level two unit) within the same cluster are trained with the randomly assigned intervention to provide care to subjects (level one unit). In this study, we derived a closed form power function and formulae for sample size determination required to detect an intervention effect on outcomes at the subject's level. In doing so, we used a test statistic based on maximum likelihood estimates from a mixed-effects linear regression model for three level data. A simulation study follows and verifies that theoretical power estimates based on the derived formulae are nearly identical to empirical estimates based on simulated data. Recommendations at the design stage of a cluster-RCT are discussed.

Original languageEnglish (US)
Pages (from-to)1256-1262
Number of pages7
JournalBiometrics
Volume64
Issue number4
DOIs
StatePublished - Dec 2008
Externally publishedYes

Fingerprint

Size determination
Randomized Trial
Statistical Power
randomized clinical trials
Health care
Linear regression
Sample Size
Maximum likelihood
Linear Models
Randomized Controlled Trials
Statistics
Likelihood Functions
Requirements
health care workers
Randomized Clinical Trial
statistics
Unit
Delivery of Health Care
sampling
Sample Size Determination

Keywords

  • Effect size
  • Power
  • Sample size
  • Three level data

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability
  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Medicine(all)

Cite this

Statistical power and sample size requirements for three level hierarchical cluster randomized trials. / Heo, Moonseong; Leon, Andrew C.

In: Biometrics, Vol. 64, No. 4, 12.2008, p. 1256-1262.

Research output: Contribution to journalArticle

Heo, Moonseong ; Leon, Andrew C. / Statistical power and sample size requirements for three level hierarchical cluster randomized trials. In: Biometrics. 2008 ; Vol. 64, No. 4. pp. 1256-1262.
@article{2e45b19930f44abd924f9141a7f88773,
title = "Statistical power and sample size requirements for three level hierarchical cluster randomized trials",
abstract = "Cluster randomized clinical trials (cluster-RCT), where the community entities serve as clusters, often yield data with three hierarchy levels. For example, interventions are randomly assigned to the clusters (level three unit). Health care professionals (level two unit) within the same cluster are trained with the randomly assigned intervention to provide care to subjects (level one unit). In this study, we derived a closed form power function and formulae for sample size determination required to detect an intervention effect on outcomes at the subject's level. In doing so, we used a test statistic based on maximum likelihood estimates from a mixed-effects linear regression model for three level data. A simulation study follows and verifies that theoretical power estimates based on the derived formulae are nearly identical to empirical estimates based on simulated data. Recommendations at the design stage of a cluster-RCT are discussed.",
keywords = "Effect size, Power, Sample size, Three level data",
author = "Moonseong Heo and Leon, {Andrew C.}",
year = "2008",
month = "12",
doi = "10.1111/j.1541-0420.2008.00993.x",
language = "English (US)",
volume = "64",
pages = "1256--1262",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Statistical power and sample size requirements for three level hierarchical cluster randomized trials

AU - Heo, Moonseong

AU - Leon, Andrew C.

PY - 2008/12

Y1 - 2008/12

N2 - Cluster randomized clinical trials (cluster-RCT), where the community entities serve as clusters, often yield data with three hierarchy levels. For example, interventions are randomly assigned to the clusters (level three unit). Health care professionals (level two unit) within the same cluster are trained with the randomly assigned intervention to provide care to subjects (level one unit). In this study, we derived a closed form power function and formulae for sample size determination required to detect an intervention effect on outcomes at the subject's level. In doing so, we used a test statistic based on maximum likelihood estimates from a mixed-effects linear regression model for three level data. A simulation study follows and verifies that theoretical power estimates based on the derived formulae are nearly identical to empirical estimates based on simulated data. Recommendations at the design stage of a cluster-RCT are discussed.

AB - Cluster randomized clinical trials (cluster-RCT), where the community entities serve as clusters, often yield data with three hierarchy levels. For example, interventions are randomly assigned to the clusters (level three unit). Health care professionals (level two unit) within the same cluster are trained with the randomly assigned intervention to provide care to subjects (level one unit). In this study, we derived a closed form power function and formulae for sample size determination required to detect an intervention effect on outcomes at the subject's level. In doing so, we used a test statistic based on maximum likelihood estimates from a mixed-effects linear regression model for three level data. A simulation study follows and verifies that theoretical power estimates based on the derived formulae are nearly identical to empirical estimates based on simulated data. Recommendations at the design stage of a cluster-RCT are discussed.

KW - Effect size

KW - Power

KW - Sample size

KW - Three level data

UR - http://www.scopus.com/inward/record.url?scp=56049108832&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56049108832&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2008.00993.x

DO - 10.1111/j.1541-0420.2008.00993.x

M3 - Article

C2 - 18266889

AN - SCOPUS:56049108832

VL - 64

SP - 1256

EP - 1262

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 4

ER -