Sample size estimation using repeated measurements on biomarkers as outcomes

Alison J. Kirby; Noya Galai; Alvaro Muñoz

doi:10.1016/0197-2456(94)90054-X

Sample size estimation using repeated measurements on biomarkers as outcomes

Alison J. Kirby, Noya Galai, Alvaro Muñoz

The International Center of Health Innovation & Nutrition in memory of Manya Igel

Research output: Contribution to journal › Article › peer-review

30 Scopus citations

Abstract

The objectives of this paper are to (1) examine methods of using longitudinal data in designing comparative trials and calculating sample sizes or power and (2) show the effect of autocorrelation of repeated measures on the assessment of sample sizes. A statistical model with a simple regression structure for the mean trajectory of the longitudinal data and a two-parameter model for the correlations of within-individual observations given by corr(y_t,y_t+s) = γ^{s^θ} is used. The methods are illustrated by considering a two-group trial and investigating the effect of different values of the correlation parameters, γ and θ on the sample size. The results show that taking account of the autocorrelation structure of longitudinal data may lead to more efficient designs. Specifically, the stronger the autocorrelation is, the smaller the sample size that is required.

Original language	English
Pages (from-to)	165-172
Number of pages	8
Journal	Controlled Clinical Trials
Volume	15
Issue number	3
DOIs	https://doi.org/10.1016/0197-2456(94)90054-X
State	Published - 1 Jan 1994

Keywords

HIV-1
autocorrelation
biological markers
longitudinal studies
sample size

ASJC Scopus subject areas

Pharmacology

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/0197-2456(94)90054-X

Cite this

@article{4447e3345e6d48eeb7f2e332c397c6e1,

title = "Sample size estimation using repeated measurements on biomarkers as outcomes",

abstract = "The objectives of this paper are to (1) examine methods of using longitudinal data in designing comparative trials and calculating sample sizes or power and (2) show the effect of autocorrelation of repeated measures on the assessment of sample sizes. A statistical model with a simple regression structure for the mean trajectory of the longitudinal data and a two-parameter model for the correlations of within-individual observations given by corr(yt,yt+s) = γsθ is used. The methods are illustrated by considering a two-group trial and investigating the effect of different values of the correlation parameters, γ and θ on the sample size. The results show that taking account of the autocorrelation structure of longitudinal data may lead to more efficient designs. Specifically, the stronger the autocorrelation is, the smaller the sample size that is required.",

keywords = "HIV-1, autocorrelation, biological markers, longitudinal studies, sample size",

author = "Kirby, {Alison J.} and Noya Galai and Alvaro Mu{\~n}oz",

note = "Funding Information: Received from the Department of Epidemiology, the Johns Hopkins School of Hygiene and Public Health, Baltimore, Maryland. Accepted for publication September 24, 1993. This work was supported by contract NO1-AI-72676 from the National Institute of Allergy and Infectious Disease. This paper was selected for presentation at the Student Scholarship session of the 14th Annual Meeting of the Society of Clinical Trials. Address correspondence to Dr. A. Kirby, Hampton House, Rm. 782, 624 North Broadway, Baltimore, MD 21205.",

year = "1994",

month = jan,

day = "1",

doi = "10.1016/0197-2456(94)90054-X",

language = "English",

volume = "15",

pages = "165--172",

journal = "Controlled Clinical Trials",

issn = "0197-2456",

publisher = "Elsevier BV",

number = "3",

}

TY - JOUR

T1 - Sample size estimation using repeated measurements on biomarkers as outcomes

AU - Kirby, Alison J.

AU - Galai, Noya

AU - Muñoz, Alvaro

N1 - Funding Information: Received from the Department of Epidemiology, the Johns Hopkins School of Hygiene and Public Health, Baltimore, Maryland. Accepted for publication September 24, 1993. This work was supported by contract NO1-AI-72676 from the National Institute of Allergy and Infectious Disease. This paper was selected for presentation at the Student Scholarship session of the 14th Annual Meeting of the Society of Clinical Trials. Address correspondence to Dr. A. Kirby, Hampton House, Rm. 782, 624 North Broadway, Baltimore, MD 21205.

PY - 1994/1/1

Y1 - 1994/1/1

N2 - The objectives of this paper are to (1) examine methods of using longitudinal data in designing comparative trials and calculating sample sizes or power and (2) show the effect of autocorrelation of repeated measures on the assessment of sample sizes. A statistical model with a simple regression structure for the mean trajectory of the longitudinal data and a two-parameter model for the correlations of within-individual observations given by corr(yt,yt+s) = γsθ is used. The methods are illustrated by considering a two-group trial and investigating the effect of different values of the correlation parameters, γ and θ on the sample size. The results show that taking account of the autocorrelation structure of longitudinal data may lead to more efficient designs. Specifically, the stronger the autocorrelation is, the smaller the sample size that is required.

AB - The objectives of this paper are to (1) examine methods of using longitudinal data in designing comparative trials and calculating sample sizes or power and (2) show the effect of autocorrelation of repeated measures on the assessment of sample sizes. A statistical model with a simple regression structure for the mean trajectory of the longitudinal data and a two-parameter model for the correlations of within-individual observations given by corr(yt,yt+s) = γsθ is used. The methods are illustrated by considering a two-group trial and investigating the effect of different values of the correlation parameters, γ and θ on the sample size. The results show that taking account of the autocorrelation structure of longitudinal data may lead to more efficient designs. Specifically, the stronger the autocorrelation is, the smaller the sample size that is required.

KW - HIV-1

KW - autocorrelation

KW - biological markers

KW - longitudinal studies

KW - sample size

UR - http://www.scopus.com/inward/record.url?scp=0028337359&partnerID=8YFLogxK

U2 - 10.1016/0197-2456(94)90054-X

DO - 10.1016/0197-2456(94)90054-X

M3 - Article

C2 - 7913674

AN - SCOPUS:0028337359

SN - 0197-2456

VL - 15

SP - 165

EP - 172

JO - Controlled Clinical Trials

JF - Controlled Clinical Trials

IS - 3

ER -

Sample size estimation using repeated measurements on biomarkers as outcomes

Abstract

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this