Sample Size Calculations for Clustered and Longitudinal Outcomes in Clinical Research  book cover
SAVE
$21.00
1st Edition

Sample Size Calculations for Clustered and Longitudinal Outcomes in Clinical Research




ISBN 9781466556263
Published December 9, 2014 by Chapman and Hall/CRC
260 Pages - 7 B/W Illustrations

 
SAVE ~ $21.00
was $105.00
USD $84.00

Prices & shipping based on shipping country


Preview

Book Description

Accurate sample size calculation ensures that clinical studies have adequate power to detect clinically meaningful effects. This results in the efficient use of resources and avoids exposing a disproportionate number of patients to experimental treatments caused by an overpowered study.

Sample Size Calculations for Clustered and Longitudinal Outcomes in Clinical Research explains how to determine sample size for studies with correlated outcomes, which are widely implemented in medical, epidemiological, and behavioral studies.

The book focuses on issues specific to the two types of correlated outcomes: longitudinal and clustered. For clustered studies, the authors provide sample size formulas that accommodate variable cluster sizes and within-cluster correlation. For longitudinal studies, they present sample size formulas to account for within-subject correlation among repeated measurements and various missing data patterns. For multiple levels of clustering, the level at which to perform randomization actually becomes a design parameter. The authors show how this can greatly impact trial administration, analysis, and sample size requirement.

Addressing the overarching theme of sample size determination for correlated outcomes, this book provides a useful resource for biostatisticians, clinical investigators, epidemiologists, and social scientists whose research involves trials with correlated outcomes. Each chapter is self-contained so readers can explore topics relevant to their research projects without having to refer to other chapters.

Table of Contents

Sample Size Determination for Independent Outcomes
Introduction
Precision Analysis
Power Analysis

Sample Size Determination for Clustered Outcomes
Introduction
One-Sample Clustered Continuous Outcomes
One-Sample Clustered Binary Outcomes
Two-Sample Clustered Continuous Outcomes
Two-Sample Clustered Binary Outcomes
Stratified Cluster Randomization for Binary Outcomes
Nonparametric Approach for One-Sample Clustered Binary Outcomes

Sample Size Determination for Repeated Measurement Outcomes Using Summary Statistics
Introduction
Information Needed for Sample Size Estimation
Summary Statistics

Sample Size Determination for Correlated Outcome Measurements Using GEE
Motivation
Review of GEE
Compare the Slope for a Continuous Outcome
Test the TAD for a Continuous Outcome
Compare the Slope for a Binary Outcome
Test the TAD for a Binary Outcome
Compare the Slope for a Count Outcome
Test the TAD for a Count Outcome

Sample Size Determination for Correlated Outcomes from Two-Level Randomized Clinical Trials
Introduction
Statistical Models for Continuous Outcomes
Testing Main Effects
Two Level Longitudinal Designs: Testing Slope Differences
Cross-Sectional Factorial Designs: Interactions between Treatments
Longitudinal Factorial Designs: Treatment Effects on Slopes
Sample Sizes for Binary Outcomes

Sample Size Determination for Correlated Outcomes from Three Level Randomized Clinical Trials
Introduction
Statistical Model for Continuous Outcomes
Testing Main Effects
Testing Slope Differences
Cross-Sectional Factorial Designs: Interactions between Treatments
Longitudinal Factorial Designs: Treatment Effects on Slopes
Sample Sizes for Binary Outcomes

Further Readings appear at the end of each chapter.

...
View More

Author(s)

Biography

Chul Ahn, PhD, is a professor in the Department of Clinical Sciences and the cancer center associate director for biostatistics and bioinformatics in the Simmons Comprehensive Cancer Center at the University of Texas Southwestern Medical Center. He is also director of Biostatistics and Research Design for the NIH-sponsored Clinical and Translational Science Award (CTSA). He has published more than 370 peer-reviewed papers addressing the design and analysis of clinical trials and epidemiological studies as well as the evaluation of repeated measurements and correlated data.

Moonseong Heo, PhD, is a professor in the Department of Epidemiology & Population Health at the Albert Einstein College of Medicine. His research includes sample size determinations for clinical trials, meta-analysis, longitudinal data analysis applying mixed-effects models, handling attrition problems in clinical trials data, and epidemiology in the fields of obesity and psychiatry.

Song Zhang, PhD, is an associate professor in the Department of Clinical Sciences at the University of Texas Southwestern Medical Center. He has extensive experience in the design of clinical trials with correlated outcomes, addressing challenges that involve different correlation structures, missing data patterns, financial constraints, and historical controls. He is also interested in Bayesian statistical methods and their application in longitudinal and survival data analysis, high-throughput data analysis, disease mapping, adaptive design for clinical trials, and missing data imputation.

Reviews

"…an excellent resource for both statisticians and practitioners undertaking prospective studies in human trials."
—International Statistical Review

" . . . this is a clearly written and sequentially well-organized book. One may find it easy to read and comprehend the various conceptual and methodological issues. To facilitate better understanding, each of the covered topic deals with illustration. I fully agree with the claim of the authors that this book may serve as a useful resource for biostatisticians, clinical investigators, epidemiologists, and social scientists whose research involves randomized trials with correlated outcomes usually classified into two types: clustered or longitudinal."
—Sada Nand Dwivedi, International Society for Clinical Biostatistics

"The book opens with an excellent summary and overview of conventional sample size analysis, including precision and power analysis. . . The book moves on to sample size calucations for clustered data."
—The American Statistician, 2016 

"This book aims to be a useful reference for those of us who are frequently asked ‘how many people will I need to recruit?’ This text provides a useful reference for those who wish to calculate the sample size for a clustered design . . . clear and accessible examples and some thoughtful reminders of key considerations."
—Beth Stuart, International Society for Clinical Biostatistics