Preface.- Survival Analysis.- Longitudinal Data Analysis.- Assessment of Diagnostic Tests and Instruments.- Analysis of Sequential Clinical Trials.- Dynamic Treatment Regimes.- Statistical Issues with Trial Data and Economic Modeling for Cost-effectiveness Evaluation.- Active-controlled Clinical Trials.- Thorough QT/QTc Clinical Trials .- Causal Inference in Cancer Clinical Trials.- Index.
This volume covers classic as well as cutting-edge topics on the analysis of clinical trial data in biomedical and psychosocial research and discusses each topic in an expository and user-friendly fashion. The intent of the book is to provide an overview of the primary statistical and data analytic issues associated with each of the selected topics, followed by a discussion of approaches for tackling such issues and available software packages for carrying out analyses. While classic topics such as survival data analysis, analysis of diagnostic test data and assessment of measurement reliability are well known and covered in depth by available topic-specific texts, this volume serves a different purpose: it provides a quick introduction to each topic for self-learning, particularly for those who have not done any formal coursework on a given topic but must learn it due to its relevance to their multidisciplinary research. In addition, the chapters on these classic topics will reflect issues particularly relevant to modern clinical trials such as longitudinal designs and new methods for analyzing data from such study designs.
The coverage of these topics provides a quick introduction to these important statistical issues and methods for addressing them. As with the classic topics, this part of the volume on modern topics will enable researchers to grasp the statistical methods for addressing these emerging issues underlying modern clinical trials and to apply them to their research studies.
Discusses cutting-edge topics Provides analysis of data from dynamic treatment regimen study design, cost-effectiveness analysis, analysis of genomic data, and causal inference to Addresses confounding issues such as concurrent medication use and mechanism of action using marginal structural and structural equation models.