Analysis Of Crossover Designs With Nonignorable Dropout
Download Analysis Of Crossover Designs With Nonignorable Dropout PDF/ePub or read online books in Mobi eBooks. Click Download or Read Online button to get Analysis Of Crossover Designs With Nonignorable Dropout book now. This website allows unlimited access to, at the time of writing, more than 1.5 million titles, including hundreds of thousands of titles in various foreign languages.
Analysis of Crossover Designs with Nonignorable Dropout
Crossover designs are subject to missing data issues as many other clinical trials. There has been considerable work in crossover designs under the assumption of ignorable dropout for continuous endpoints. This thesis addresses the analysis of crossover designs with nonignorable dropout to fill in the gap. We study a comprehensive family of crossover designs, including (1) non-repeated measurements crossover designs (with one measurement per period), consisting of non-replicated treatment designs and replicated treatment designs, and (2) repeated measurements crossover designs (with more than one measurement per period) separately. The primary objective is to compare the treatment mean effects. For non-repeated measurements crossover designs, we jointly model the longitudinal measurements and the discrete time to dropout, apply maximum likelihood for parameter estimation, and propose a controlled multiple imputation method as a sensitivity analysis of the untestable missing data mechanism assumption. First, for continuous endpoints, we propose shared-parameter models and mixed-effects selection models, where we adapt a linear mixed-effects model as the conditional model for the longitudinal outcomes and invoke a discrete-time hazards model for the conditional distribution of time to dropout. We perform simulation studies to investigate the robustness of our proposed approaches under various missing data mechanisms. Second, we examine crossover designs with missing data due to ignorable and nonignorable dropout in another common type of outcomes, longitudinal binary data. We evaluate available conditional and marginal models and establish the relationship between the conditional and marginal parameters. We perform extensive simulation studies to investigate these models under complete data and the mixed-effects selection models under missing data with different parametric distributions and missingness patterns and mechanisms. Generalized estimating equations and the generalized linear mixed-effects models with pseudo-likelihood estimation are advocated for valid and robust inference. We implement the proposed models and the sensitivity analysis in real data examples based on two crossover trials. Lastly, we consider an increasingly prevalent crossover design, the repeated measurements design with intensive longitudinal data, to study the dynamic nature and the evolution of some processes. We evaluate and apply well-defined linear mixed-effects models and time-varying coefficients models to tackle the critical task of modeling time dependencies and serial correlations created by repeated measurements. The proposed models provide a powerful and reliable toolbox to analyze the crossover trials with missingness.
Design and Analysis of Cross-Over Trials, Second Edition
The first edition of Design and Analysis of Cross-Over Trials quickly became the standard reference on the subject and has remained so for more than 12 years. In that time, however, the use of cross-over trials has grown rapidly, particularly in the pharmaceutical arena, and researchers have made a number of advances in both the theory and methods applicable to these trials. Completely revised and updated, the long-awaited second edition of this classic text retains its predecessor's careful balance of theory and practice while incorporating new approaches, more data sets, and a broader scope. Enhancements in the second edition include: A new chapter on bioequivalence Recently developed methods for analyzing longitudinal continuous and categorical data Real-world examples using the SAS system A comprehensive catalog of designs, datasets, and SAS programs available on a companion Web site at www.crcpress.com The authors' exposition gives a clear, unified account of the design and analysis of cross-over trials from a statistical perspective along with their methodological underpinnings. With SAS programs and a thorough treatment of design issues, Design and Analysis of Cross-Over Trials, Second Edition sets a new standard for texts in this area and undoubtedly will be of direct practical value for years to come.
Pharmacometrics
Pharmacometrics is the science of interpreting and describing pharmacology in a quantitative fashion. The pharmaceutical industry is integrating pharmacometrics into its drug development program, but there is a lack of and need for experienced pharmacometricians since fewer and fewer academic programs exist to train them. Pharmacometrics: The Science of Quantitative Pharmacology lays out the science of pharmacometrics and its application to drug development, evaluation, and patient pharmacotherapy, providing a comprehensive set of tools for the training and development of pharmacometricians. Edited and written by key leaders in the field, this flagship text on pharmacometrics: Integrates theory and practice to let the reader apply principles and concepts. Provides a comprehensive set of tools for training and developing expertise in the pharmacometric field. Is unique in including computer code information with the examples. This volume is an invaluable resource for all pharmacometricians, statisticians, teachers, graduate and undergraduate students in academia, industry, and regulatory agencies.