Sample size calculations for group randomized trials with unequal group sizes through Monte Carlo simulations

Yang Shi, Ji Hyun Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Group randomized trial design is common in cancer prevention and health promotion research with intervention development. Several methods have been developed to handle the design and analytical issues for group randomized trial including the intraclass correlation coefficient. The widely used methods for the sample size calculation for the group randomized trial assume equal sizes across groups. In practice this assumption often fails and group randomized trial studies suffer from considerably lower statistical power than as planned. A few studies have developed sample size calculation methods for unequal group sizes, but most of them are limited to continuous outcomes. In this study, we develop a method for sample size calculation for group randomized trial studies with unequal group sizes based on Monte Carlo simulation in the mixed effect model framework. This approach incorporates the variation of group sizes and can be applied to group randomized trials with different types of outcomes. Further, it is easy to implement and can be applied to most commonly used group randomized trial designs such as pre-and-post cross-sectional and cohort study designs. We demonstrate the application of the proposed approach to two-arm group randomized trial studies with continuous and binary outcomes through simulations and analysis of a real group randomized trial dataset.

Original languageEnglish (US)
Pages (from-to)2569-2580
Number of pages12
JournalStatistical Methods in Medical Research
Volume27
Issue number9
DOIs
StatePublished - Sep 1 2018

Fingerprint

Sample Size Calculation
Randomized Trial
Unequal
Sample Size
Monte Carlo Simulation
Health Promotion
Cohort Studies
Cross-Sectional Studies
Research
Intraclass Correlation Coefficient
Neoplasms
Binary Outcomes
Mixed Effects Model
Cohort Study
Statistical Power

Keywords

  • Monte Carlo simulation
  • Sample size calculation
  • group randomized trials
  • mixed effects model
  • unequal group size

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability
  • Health Information Management

Cite this

Sample size calculations for group randomized trials with unequal group sizes through Monte Carlo simulations. / Shi, Yang; Lee, Ji Hyun.

In: Statistical Methods in Medical Research, Vol. 27, No. 9, 01.09.2018, p. 2569-2580.

Research output: Contribution to journalArticle

@article{1dff80daa3ef455db7bb81828acfb936,
title = "Sample size calculations for group randomized trials with unequal group sizes through Monte Carlo simulations",
abstract = "Group randomized trial design is common in cancer prevention and health promotion research with intervention development. Several methods have been developed to handle the design and analytical issues for group randomized trial including the intraclass correlation coefficient. The widely used methods for the sample size calculation for the group randomized trial assume equal sizes across groups. In practice this assumption often fails and group randomized trial studies suffer from considerably lower statistical power than as planned. A few studies have developed sample size calculation methods for unequal group sizes, but most of them are limited to continuous outcomes. In this study, we develop a method for sample size calculation for group randomized trial studies with unequal group sizes based on Monte Carlo simulation in the mixed effect model framework. This approach incorporates the variation of group sizes and can be applied to group randomized trials with different types of outcomes. Further, it is easy to implement and can be applied to most commonly used group randomized trial designs such as pre-and-post cross-sectional and cohort study designs. We demonstrate the application of the proposed approach to two-arm group randomized trial studies with continuous and binary outcomes through simulations and analysis of a real group randomized trial dataset.",
keywords = "Monte Carlo simulation, Sample size calculation, group randomized trials, mixed effects model, unequal group size",
author = "Yang Shi and Lee, {Ji Hyun}",
year = "2018",
month = "9",
day = "1",
doi = "10.1177/0962280216682775",
language = "English (US)",
volume = "27",
pages = "2569--2580",
journal = "Statistical Methods in Medical Research",
issn = "0962-2802",
publisher = "SAGE Publications Ltd",
number = "9",

}

TY - JOUR

T1 - Sample size calculations for group randomized trials with unequal group sizes through Monte Carlo simulations

AU - Shi, Yang

AU - Lee, Ji Hyun

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Group randomized trial design is common in cancer prevention and health promotion research with intervention development. Several methods have been developed to handle the design and analytical issues for group randomized trial including the intraclass correlation coefficient. The widely used methods for the sample size calculation for the group randomized trial assume equal sizes across groups. In practice this assumption often fails and group randomized trial studies suffer from considerably lower statistical power than as planned. A few studies have developed sample size calculation methods for unequal group sizes, but most of them are limited to continuous outcomes. In this study, we develop a method for sample size calculation for group randomized trial studies with unequal group sizes based on Monte Carlo simulation in the mixed effect model framework. This approach incorporates the variation of group sizes and can be applied to group randomized trials with different types of outcomes. Further, it is easy to implement and can be applied to most commonly used group randomized trial designs such as pre-and-post cross-sectional and cohort study designs. We demonstrate the application of the proposed approach to two-arm group randomized trial studies with continuous and binary outcomes through simulations and analysis of a real group randomized trial dataset.

AB - Group randomized trial design is common in cancer prevention and health promotion research with intervention development. Several methods have been developed to handle the design and analytical issues for group randomized trial including the intraclass correlation coefficient. The widely used methods for the sample size calculation for the group randomized trial assume equal sizes across groups. In practice this assumption often fails and group randomized trial studies suffer from considerably lower statistical power than as planned. A few studies have developed sample size calculation methods for unequal group sizes, but most of them are limited to continuous outcomes. In this study, we develop a method for sample size calculation for group randomized trial studies with unequal group sizes based on Monte Carlo simulation in the mixed effect model framework. This approach incorporates the variation of group sizes and can be applied to group randomized trials with different types of outcomes. Further, it is easy to implement and can be applied to most commonly used group randomized trial designs such as pre-and-post cross-sectional and cohort study designs. We demonstrate the application of the proposed approach to two-arm group randomized trial studies with continuous and binary outcomes through simulations and analysis of a real group randomized trial dataset.

KW - Monte Carlo simulation

KW - Sample size calculation

KW - group randomized trials

KW - mixed effects model

KW - unequal group size

UR - http://www.scopus.com/inward/record.url?scp=85051790842&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051790842&partnerID=8YFLogxK

U2 - 10.1177/0962280216682775

DO - 10.1177/0962280216682775

M3 - Article

AN - SCOPUS:85051790842

VL - 27

SP - 2569

EP - 2580

JO - Statistical Methods in Medical Research

JF - Statistical Methods in Medical Research

SN - 0962-2802

IS - 9

ER -