Surrogate endpoint evaluation has been a very active area of research ever since the seminal papers by Ross Prentice, Laurence Freedman, and their coauthors, in the late 1980s and early 1990s. The original singe-trial work was followed by meta-analytic developments. Later, information-theoretic methodology was introduced. Research followed both the path of association as well as causal inference. Recently, efforts have been undertaken to study similarities and differences between these strands. However, methodological development is worth very little in the absence of two crucial resources.
The first resource is data. It is now broadly accepted that surrogate endpoint evaluation in practice is best done from a multi-trial perspective, implying that large volumes of data are needed. Arguably, data should be made available by a variety of companies and other sponsors to provide the necessary critical data volume. The second resource is software. No matter how appealing a model or other methodological approach is user-friendly software in broadly accessible platforms is needed to allow for and to promote its use.
Starting from a general methodological overview, covering a variety of situations in terms of (true and surrogate endpoint) outcome types and therapeutic areas, contemporary surrogate endpoint evaluation tools are described. These are accompanied by software implementations. This book focuses on both SAS and R; for the latter Shiny Apps are also developed. Software is described in a tutorial fashion, illustrated by means of real examples, and made available via the authors’ web pages.
The authors gratefully acknowledge contributions from a number of additional chapter-specific authors. We would also like to thank John Kimmel, Statistics Editor at Chapman & Hall/CRC Press, for his encouragement and expert advice throughout all stages of this project.
Financial support from the IAP research network #P7/06 of the Belgian Government (Belgian Science Policy) is gratefully acknowledged. Part of the research reported in this book was supported by funding received from the European Seventh Framework programme FP7 2007-2013 under grant agreement Nr. 602552 and by funding from the IWT-SBO ExaScience grant.
Ariel Alonso, Theophile Bigirumurame, Tomasz Burzykowski, Marc Buyse, Geert Molenberghs, Leacky Muchene, Nolen Joy Perualila, Ziv Shkedy, Wim Van der Elst