Table of Contents

Background and Setting. Introduction. Objectives and estimands–determining what to estimate. Study design–collecting the intended data. Example data. Mixed effects models review.

Modeling the observed data. Choice of dependent variable and statistical test. modeling covariance (correlation). Modeling means over time. Accounting for covariates. Categorical data. Model checking and verification.

Methods for dealing with missing Data. Overview of missing data. Simple and ad hoc Approaches for dealing with missing data. Direct maximum likelihood. Multiple imputation. Inverse probability. Methods for incomplete categorical data weighted generalized estimated equations. Doubly robust methods. MNAR methods. Methods for incomplete categorical data.

A comprehensive approach to study development and analyses. Developing statistical analysis plans. Example analyses of clinical trial data.

About the Author

Craig Mallinckrodt and Ilya Lipkovich each have extensive experience in medical research and longitudinal analyses. Dr. Mallinckrodt is a Research Fellow at Eli Lilly and Company and a Fellow of the American Statistical Association. He has won numerous awards, including the 2014 award for statistical excellence in the Pharmaceutical Industry from the Royal Statistical Society and PSI (Statisticians in the Pharmaceutical Industry). Dr. Lipkovich is a Principal Scientific Advisor at Quintiles. He is a widely-published author and frequent presenter at conferences and has developed a number of successful short courses and tutorials.

Reviews

"This book deals mostly with longitudinal clinical trial data, but also with the related issue of imputing missing data. The book is an excellent resource overall, as it is fairly comprehensive, well referenced, and clear."
~Vance W. Berger, PhD, NIH/NCI/DCP/BRGAnalyzing Longitudinal Clinical Trial Data provides, in a well organized and small format, a fairly easy read that could be helpful for both researchers analyzing longitudinal data collected from clinical trials (or perhaps even observational studies) and instructors teaching undergraduate and graduate courses on clinical trials, longitudinal data, and missing data. The book is divided into four well-structured and complementary sections: background and setting, general modeling strategies and methods, methods for dealing with missing data, and overall guidance (with illustration) for developing a study.
~Journal of the American Statistical Association "I recommend this book to anyone who deals with longitudinal clinical trials data at any level with confidence as it concisely presents essential ideas and analysis techniques with illustrative examples, in an intuitively appealing way, both on analytic and conceptual levels. It addresses an important need for practicing (bio)statisticians."
~Biometrical Journal