Sample size estimation for a two-group comparison of repeated count outcomes using GEE

Ying Lou, Jing Cao, Song Zhang, Chul Ahn

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Randomized clinical trials with count measurements as the primary outcome are common in various medical areas such as seizure counts in epilepsy trials, or relapse counts in multiple sclerosis trials. Controlled clinical trials frequently use a conventional parallel-group design that assigns subjects randomly to one of two treatment groups and repeatedly evaluates them at baseline and intervals across a treatment period of a fixed duration. The primary interest is to compare the rates of change between treatment groups. Generalized estimating equations (GEEs) have been widely used to compare rates of change between treatment groups because of its robustness to misspecification of the true correlation structure. In this paper, we derive a sample size formula for comparing the rates of change between two groups in a repeatedly measured count outcome using GEE. The sample size formula incorporates general missing patterns such as independent missing and monotone missing, and general correlation structures such as AR(1) and compound symmetry (CS). The performance of the sample size formula is evaluated through simulation studies. Sample size estimation is illustrated by a clinical trial example from epilepsy.

Original languageEnglish (US)
Pages (from-to)1-11
Number of pages11
JournalCommunications in Statistics - Theory and Methods
DOIs
StateAccepted/In press - Mar 11 2017

Fingerprint

Generalized Estimating Equations
Count
Sample Size
Rate of change
Epilepsy
Correlation Structure
Clinical Trials
Compound Symmetry
Multiple Sclerosis
Randomized Clinical Trial
Misspecification
Assign
Baseline
Monotone
Simulation Study
Robustness
Interval
Evaluate

Keywords

  • Count outcome
  • GEE
  • missing data
  • repeated measurements
  • sample size.

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

@article{daac121eda5440979188d3e095137b95,
title = "Sample size estimation for a two-group comparison of repeated count outcomes using GEE",
abstract = "Randomized clinical trials with count measurements as the primary outcome are common in various medical areas such as seizure counts in epilepsy trials, or relapse counts in multiple sclerosis trials. Controlled clinical trials frequently use a conventional parallel-group design that assigns subjects randomly to one of two treatment groups and repeatedly evaluates them at baseline and intervals across a treatment period of a fixed duration. The primary interest is to compare the rates of change between treatment groups. Generalized estimating equations (GEEs) have been widely used to compare rates of change between treatment groups because of its robustness to misspecification of the true correlation structure. In this paper, we derive a sample size formula for comparing the rates of change between two groups in a repeatedly measured count outcome using GEE. The sample size formula incorporates general missing patterns such as independent missing and monotone missing, and general correlation structures such as AR(1) and compound symmetry (CS). The performance of the sample size formula is evaluated through simulation studies. Sample size estimation is illustrated by a clinical trial example from epilepsy.",
keywords = "Count outcome, GEE, missing data, repeated measurements, sample size.",
author = "Ying Lou and Jing Cao and Song Zhang and Chul Ahn",
year = "2017",
month = "3",
day = "11",
doi = "10.1080/03610926.2015.1134572",
language = "English (US)",
pages = "1--11",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Sample size estimation for a two-group comparison of repeated count outcomes using GEE

AU - Lou, Ying

AU - Cao, Jing

AU - Zhang, Song

AU - Ahn, Chul

PY - 2017/3/11

Y1 - 2017/3/11

N2 - Randomized clinical trials with count measurements as the primary outcome are common in various medical areas such as seizure counts in epilepsy trials, or relapse counts in multiple sclerosis trials. Controlled clinical trials frequently use a conventional parallel-group design that assigns subjects randomly to one of two treatment groups and repeatedly evaluates them at baseline and intervals across a treatment period of a fixed duration. The primary interest is to compare the rates of change between treatment groups. Generalized estimating equations (GEEs) have been widely used to compare rates of change between treatment groups because of its robustness to misspecification of the true correlation structure. In this paper, we derive a sample size formula for comparing the rates of change between two groups in a repeatedly measured count outcome using GEE. The sample size formula incorporates general missing patterns such as independent missing and monotone missing, and general correlation structures such as AR(1) and compound symmetry (CS). The performance of the sample size formula is evaluated through simulation studies. Sample size estimation is illustrated by a clinical trial example from epilepsy.

AB - Randomized clinical trials with count measurements as the primary outcome are common in various medical areas such as seizure counts in epilepsy trials, or relapse counts in multiple sclerosis trials. Controlled clinical trials frequently use a conventional parallel-group design that assigns subjects randomly to one of two treatment groups and repeatedly evaluates them at baseline and intervals across a treatment period of a fixed duration. The primary interest is to compare the rates of change between treatment groups. Generalized estimating equations (GEEs) have been widely used to compare rates of change between treatment groups because of its robustness to misspecification of the true correlation structure. In this paper, we derive a sample size formula for comparing the rates of change between two groups in a repeatedly measured count outcome using GEE. The sample size formula incorporates general missing patterns such as independent missing and monotone missing, and general correlation structures such as AR(1) and compound symmetry (CS). The performance of the sample size formula is evaluated through simulation studies. Sample size estimation is illustrated by a clinical trial example from epilepsy.

KW - Count outcome

KW - GEE

KW - missing data

KW - repeated measurements

KW - sample size.

UR - http://www.scopus.com/inward/record.url?scp=85015106393&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015106393&partnerID=8YFLogxK

U2 - 10.1080/03610926.2015.1134572

DO - 10.1080/03610926.2015.1134572

M3 - Article

AN - SCOPUS:85015106393

SP - 1

EP - 11

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

ER -