Multiple Testing Problems in Pharmaceutical Statistics

Multiple Testing Problems in Pharmaceutical Statistics is a book that discusses the rapidly growing area of multiple comparison research with an emphasis on pharmaceutical applications. It provides practical examples from recent trials and covers statistical methods for analyzing clinical dose response studies, multiple endpoints, adaptive designs, and pharmacogenomic studies. The book explains how to solve critical issues in multiple testing encountered in pre-clinical and clinical trial applications and presents the necessary statistical methodology with examples and software code.

Format: Paperback / softback
Length: 322 pages
Publication date: 21 January 2023
Publisher: Taylor & Francis Ltd

Multiple Testing Problems in Pharmaceutical Statistics is a comprehensive guide that brings together leading statisticians, scientists, and clinicians from the pharmaceutical industry, academia, and regulatory agencies to explore the rapidly growing area of multiple comparison research with an emphasis on pharmaceutical applications. In this book, expert contributors delve into important multiplicity problems encountered in pre-clinical and clinical trial settings, providing valuable insights and practical solutions.

The book begins with a broad introduction that provides a regulatory perspective on different types of multiplicity problems commonly encountered in confirmatory controlled clinical trials. It then offers an overview of the concepts, principles, and procedures of multiple testing, laying the foundation for the subsequent chapters.

Chapter 1 delves into statistical methods for analyzing clinical dose response studies that compare multiple dose levels with a control. The contributors discuss the use of statistical models, such as linear and nonlinear mixed models, to account for the correlation between repeated measurements and the potential for confounding factors. They also explore the application of Bayesian methods, such as hierarchical Bayesian models, to address multiplicity issues and estimate treatment effects.

Chapter 2 focuses on statistical methods for analyzing multiple endpoints in clinical trials. The authors discuss the use of composite endpoints, such as survival curves, to evaluate the overall efficacy of treatments. They also explore the use of multi-criteria decision analysis (MCDA) to prioritize treatments based on a combination of efficacy and safety outcomes.

Chapter 3 explores gatekeeping procedures for testing hierarchically ordered hypotheses, which are commonly used in clinical trials to control the false discovery rate. The contributors discuss the use of significance tests, such as Bonferroni and Holm-Bonferroni adjustments, to adjust p-values and control the familywise error rate. They also introduce the concept of sequential testing and discuss its advantages and disadvantages.

Chapter 4 discusses statistical approaches for the design and analysis of adaptive designs and related confirmatory hypothesis testing problems. Adaptive designs allow for the adjustment of sample sizes and treatment allocation based on interim data, reducing the number of subjects required and minimizing the risk of Type I errors. The authors discuss the use of Bayesian methods, such as Markov chain Monte Carlo (MCMC) methods, to estimate treatment effects and perform hypothesis testing in adaptive designs.

Chapter 5 focuses on the design of pharmacogenomic studies based on established statistical principles. The authors discuss the use of genetic data to identify biomarkers that predict treatment response and develop personalized treatment strategies. They also explore the analysis of data collected in these studies, taking into account the numerous multiplicity issues that occur, such as multiple testing, multiple comparisons, and confounding.

Chapter 6 concludes the book by summarizing the key findings and providing practical examples from recent trials. The contributors showcase how statistical methods have been applied to address multiplicity issues in pharmaceutical research, leading to improved drug development and patient outcomes.

In conclusion, Multiple Testing Problems in Pharmaceutical Statistics is a valuable resource for statisticians, scientists, and clinicians involved in pharmaceutical research. It provides a comprehensive and up-to-date overview of the statistical methodologies and techniques used to address multiplicity problems in pre-clinical and clinical trial applications. With its practical examples and software code, the book enables readers to apply the methods in practice and solve critical issues in multiple testing encountered in their research. This volume is essential for anyone seeking to advance their understanding of pharmaceutical statistics and improve the efficiency and effectiveness of drug development.

Weight: 600g
Dimension: 234 x 156 (mm)
ISBN-13: 9781032477701