Sample size for a two-group comparison of repeated binary measurements using GEE

Sin Ho Jung, Chul W. Ahn

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Controlled clinical trials often randomize subjects to two treatment groups and repeatedly evaluate them at baseline and intervals across a treatment period of fixed duration. A popular primary objective in these trials is to compare the change rates in the repeated measurements between treatment groups. Repeated measurements usually involve missing data and a serial correlation within each subject. The generalized estimating equation (GEE) method has been widely used to fit the time trend in repeated measurements because of its robustness to random missing and misspecification of the true correlation structure. In this paper, we propose a closed form sample size formula for comparing the change rates of binary repeated measurements using GEE for a two-group comparison. The sample size formula is derived incorporating missing patterns, such as independent missing and monotone missing, and correlation structures, such as AR(1) model. We also propose an algorithm to generate correlated binary data with arbitrary marginal means and a Markov dependency and use it in simulation studies.

Original languageEnglish (US)
Pages (from-to)2583-2596
Number of pages14
JournalStatistics in Medicine
Volume24
Issue number17
DOIs
StatePublished - Sep 15 2005

Fingerprint

Repeated Measurements
Generalized Estimating Equations
Sample Size
Binary
Correlation Structure
Controlled Clinical Trials
Correlated Binary Data
Serial Correlation
Misspecification
Rate of change
Missing Data
Clinical Trials
Baseline
Monotone
Closed-form
Simulation Study
Robustness
Interval
Evaluate
Arbitrary

Keywords

  • AR(1)
  • Independent missing
  • Missing completely at random
  • Monotone missing
  • Working independent correlation

ASJC Scopus subject areas

  • Epidemiology

Cite this

Sample size for a two-group comparison of repeated binary measurements using GEE. / Jung, Sin Ho; Ahn, Chul W.

In: Statistics in Medicine, Vol. 24, No. 17, 15.09.2005, p. 2583-2596.

Research output: Contribution to journalArticle

@article{31a6d8e14a594b2ca8c88489ce81a452,
title = "Sample size for a two-group comparison of repeated binary measurements using GEE",
abstract = "Controlled clinical trials often randomize subjects to two treatment groups and repeatedly evaluate them at baseline and intervals across a treatment period of fixed duration. A popular primary objective in these trials is to compare the change rates in the repeated measurements between treatment groups. Repeated measurements usually involve missing data and a serial correlation within each subject. The generalized estimating equation (GEE) method has been widely used to fit the time trend in repeated measurements because of its robustness to random missing and misspecification of the true correlation structure. In this paper, we propose a closed form sample size formula for comparing the change rates of binary repeated measurements using GEE for a two-group comparison. The sample size formula is derived incorporating missing patterns, such as independent missing and monotone missing, and correlation structures, such as AR(1) model. We also propose an algorithm to generate correlated binary data with arbitrary marginal means and a Markov dependency and use it in simulation studies.",
keywords = "AR(1), Independent missing, Missing completely at random, Monotone missing, Working independent correlation",
author = "Jung, {Sin Ho} and Ahn, {Chul W.}",
year = "2005",
month = "9",
day = "15",
doi = "10.1002/sim.2136",
language = "English (US)",
volume = "24",
pages = "2583--2596",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "17",

}

TY - JOUR

T1 - Sample size for a two-group comparison of repeated binary measurements using GEE

AU - Jung, Sin Ho

AU - Ahn, Chul W.

PY - 2005/9/15

Y1 - 2005/9/15

N2 - Controlled clinical trials often randomize subjects to two treatment groups and repeatedly evaluate them at baseline and intervals across a treatment period of fixed duration. A popular primary objective in these trials is to compare the change rates in the repeated measurements between treatment groups. Repeated measurements usually involve missing data and a serial correlation within each subject. The generalized estimating equation (GEE) method has been widely used to fit the time trend in repeated measurements because of its robustness to random missing and misspecification of the true correlation structure. In this paper, we propose a closed form sample size formula for comparing the change rates of binary repeated measurements using GEE for a two-group comparison. The sample size formula is derived incorporating missing patterns, such as independent missing and monotone missing, and correlation structures, such as AR(1) model. We also propose an algorithm to generate correlated binary data with arbitrary marginal means and a Markov dependency and use it in simulation studies.

AB - Controlled clinical trials often randomize subjects to two treatment groups and repeatedly evaluate them at baseline and intervals across a treatment period of fixed duration. A popular primary objective in these trials is to compare the change rates in the repeated measurements between treatment groups. Repeated measurements usually involve missing data and a serial correlation within each subject. The generalized estimating equation (GEE) method has been widely used to fit the time trend in repeated measurements because of its robustness to random missing and misspecification of the true correlation structure. In this paper, we propose a closed form sample size formula for comparing the change rates of binary repeated measurements using GEE for a two-group comparison. The sample size formula is derived incorporating missing patterns, such as independent missing and monotone missing, and correlation structures, such as AR(1) model. We also propose an algorithm to generate correlated binary data with arbitrary marginal means and a Markov dependency and use it in simulation studies.

KW - AR(1)

KW - Independent missing

KW - Missing completely at random

KW - Monotone missing

KW - Working independent correlation

UR - http://www.scopus.com/inward/record.url?scp=24944437239&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24944437239&partnerID=8YFLogxK

U2 - 10.1002/sim.2136

DO - 10.1002/sim.2136

M3 - Article

C2 - 16118812

AN - SCOPUS:24944437239

VL - 24

SP - 2583

EP - 2596

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 17

ER -