Sample size considerations for stratified cluster randomization design with binary outcomes and varying cluster size

Xiaohan Xu, Hong Zhu, Chul Ahn

Research output: Contribution to journalArticle

Abstract

Stratified cluster randomization trials (CRTs) have been frequently employed in clinical and healthcare research. Comparing with simple randomized CRTs, stratified CRTs reduce the imbalance of baseline prognostic factors among different intervention groups. Due to the popularity, there has been a growing interest in methodological development on sample size estimation and power analysis for stratified CRTs; however, existing work mostly assumes equal cluster size within each stratum and uses multilevel models. Clusters are often naturally formed with random sizes in CRTs. With varying cluster size, commonly used ad hoc approaches ignore the variability in cluster size, which may underestimate (overestimate) the required number of clusters for each group per stratum and lead to underpowered (overpowered) clinical trials. We propose closed-form sample size formulas for estimating the required total number of subjects and for estimating the number of clusters for each group per stratum, based on Cochran-Mantel-Haenszel statistic for stratified cluster randomization design with binary outcomes, accounting for both clustering and varying cluster size. We investigate the impact of various design parameters on the relative change in the required number of clusters for each group per stratum due to varying cluster size. Simulation studies are conducted to evaluate the finite-sample performance of the proposed sample size method. A real application example of a pragmatic stratified CRT of a triad of chronic kidney disease, diabetes, and hypertension is presented for illustration.

Original languageEnglish (US)
JournalStatistics in Medicine
DOIs
StatePublished - Jan 1 2019

Fingerprint

Binary Outcomes
Random Allocation
Randomisation
Sample Size
Cluster Analysis
Number of Clusters
Health Services Research
Design
Chronic Renal Insufficiency
Clinical Trials
Prognostic Factors
Hypertension
Multilevel Models
Power Analysis
Diabetes
Kidney
Parameter Design
Healthcare
Statistic
Baseline

Keywords

  • binary outcomes
  • cluster randomization design
  • sample size
  • stratification
  • varying cluster size

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

@article{00951655165f4cc0b53718946c3b8303,
title = "Sample size considerations for stratified cluster randomization design with binary outcomes and varying cluster size",
abstract = "Stratified cluster randomization trials (CRTs) have been frequently employed in clinical and healthcare research. Comparing with simple randomized CRTs, stratified CRTs reduce the imbalance of baseline prognostic factors among different intervention groups. Due to the popularity, there has been a growing interest in methodological development on sample size estimation and power analysis for stratified CRTs; however, existing work mostly assumes equal cluster size within each stratum and uses multilevel models. Clusters are often naturally formed with random sizes in CRTs. With varying cluster size, commonly used ad hoc approaches ignore the variability in cluster size, which may underestimate (overestimate) the required number of clusters for each group per stratum and lead to underpowered (overpowered) clinical trials. We propose closed-form sample size formulas for estimating the required total number of subjects and for estimating the number of clusters for each group per stratum, based on Cochran-Mantel-Haenszel statistic for stratified cluster randomization design with binary outcomes, accounting for both clustering and varying cluster size. We investigate the impact of various design parameters on the relative change in the required number of clusters for each group per stratum due to varying cluster size. Simulation studies are conducted to evaluate the finite-sample performance of the proposed sample size method. A real application example of a pragmatic stratified CRT of a triad of chronic kidney disease, diabetes, and hypertension is presented for illustration.",
keywords = "binary outcomes, cluster randomization design, sample size, stratification, varying cluster size",
author = "Xiaohan Xu and Hong Zhu and Chul Ahn",
year = "2019",
month = "1",
day = "1",
doi = "10.1002/sim.8175",
language = "English (US)",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Sample size considerations for stratified cluster randomization design with binary outcomes and varying cluster size

AU - Xu, Xiaohan

AU - Zhu, Hong

AU - Ahn, Chul

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Stratified cluster randomization trials (CRTs) have been frequently employed in clinical and healthcare research. Comparing with simple randomized CRTs, stratified CRTs reduce the imbalance of baseline prognostic factors among different intervention groups. Due to the popularity, there has been a growing interest in methodological development on sample size estimation and power analysis for stratified CRTs; however, existing work mostly assumes equal cluster size within each stratum and uses multilevel models. Clusters are often naturally formed with random sizes in CRTs. With varying cluster size, commonly used ad hoc approaches ignore the variability in cluster size, which may underestimate (overestimate) the required number of clusters for each group per stratum and lead to underpowered (overpowered) clinical trials. We propose closed-form sample size formulas for estimating the required total number of subjects and for estimating the number of clusters for each group per stratum, based on Cochran-Mantel-Haenszel statistic for stratified cluster randomization design with binary outcomes, accounting for both clustering and varying cluster size. We investigate the impact of various design parameters on the relative change in the required number of clusters for each group per stratum due to varying cluster size. Simulation studies are conducted to evaluate the finite-sample performance of the proposed sample size method. A real application example of a pragmatic stratified CRT of a triad of chronic kidney disease, diabetes, and hypertension is presented for illustration.

AB - Stratified cluster randomization trials (CRTs) have been frequently employed in clinical and healthcare research. Comparing with simple randomized CRTs, stratified CRTs reduce the imbalance of baseline prognostic factors among different intervention groups. Due to the popularity, there has been a growing interest in methodological development on sample size estimation and power analysis for stratified CRTs; however, existing work mostly assumes equal cluster size within each stratum and uses multilevel models. Clusters are often naturally formed with random sizes in CRTs. With varying cluster size, commonly used ad hoc approaches ignore the variability in cluster size, which may underestimate (overestimate) the required number of clusters for each group per stratum and lead to underpowered (overpowered) clinical trials. We propose closed-form sample size formulas for estimating the required total number of subjects and for estimating the number of clusters for each group per stratum, based on Cochran-Mantel-Haenszel statistic for stratified cluster randomization design with binary outcomes, accounting for both clustering and varying cluster size. We investigate the impact of various design parameters on the relative change in the required number of clusters for each group per stratum due to varying cluster size. Simulation studies are conducted to evaluate the finite-sample performance of the proposed sample size method. A real application example of a pragmatic stratified CRT of a triad of chronic kidney disease, diabetes, and hypertension is presented for illustration.

KW - binary outcomes

KW - cluster randomization design

KW - sample size

KW - stratification

KW - varying cluster size

UR - http://www.scopus.com/inward/record.url?scp=85065199468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065199468&partnerID=8YFLogxK

U2 - 10.1002/sim.8175

DO - 10.1002/sim.8175

M3 - Article

C2 - 31033011

AN - SCOPUS:85065199468

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

ER -