Statistical Evaluation of Surrogate Endpoints in Clinical Trials


Prof. Geert Molenberghs (Universiteit Hasselt and Katholieke Universiteit Leuven, Belgium).

Half-day course

Total duration: 3 hours 15 minutes.

Sign up

Click on the button to sign up for this Instant Short Course. It takes less than 5 minutes.

$499.00 (U.S. dollars)
7-day access for up to 25 attendees


Both humanitarian and commercial considerations have spurred intensive search for methods to reduce the time and cost required to develop new therapies. The identification and use of surrogate endpoints, i.e. measures that can replace or supplement other endpoints in evaluations of experimental treatments or other interventions, is a general strategy that has stimulated much enthusiasm. Surrogate endpoints are useful when they can be measured earlier, more conveniently, or more frequently than the “true” endpoints of primary interest (Ellenberg and Hamilton, Statistics in Medicine, 1989). Regulatory agencies around the globe, particularly in the United States, Europe, and Japan, are introducing provisions and policies relating to the use of surrogate endpoints in registration studies. But how can one establish the adequacy of a surrogate, in the sense that treatment effectiveness on the surrogate will accurately predict treatment effect on the intended, and more important, true outcome? What kind of evidence is needed, and what statistical methods portray that evidence most appropriately?

The validation of surrogate endpoints has been studied by Prentice (Statistics in Medicine, 1989), who presented a definition of validity as well as a formal set of criteria that are equivalent if both the surrogate and true endpoints are binary. Freedman, Graubard, and Schatzkin (Statistics in Medicine, 1992) supplemented these criteria with the proportion explained which, conceptually, is the fraction of the treatment effect mediated by the surrogate. Noting operational difficulties with the proportion explained, Buyse and Molenberghs (Biometrics, 1998) proposed instead to use jointly the within-treatment partial association of true and surrogate responses, and the treatment effect on the surrogate relative to that on the true outcome. In a multi-center setting, these quantities can be generalized to individual-level and trial-level measures of surrogacy.

Buyse et al. (Biostatistics, 2000) therefore have therefore proposed a meta-analytic framework to study surrogacy at both the trial and individual-patient levels. A number of variations of the theme have been developed, depending on the type of endpoint for the true and surrogate endpoint, respectively, and depending on the focus of the evaluation exercise. At the same time, efforts have been made to converge to a common framework, encompassing the wide variety of settings one can encounter. This includes a so-called variance reducation factor and an information-theoretic approach. Further, work has been done to convert the evaluation methodology to sample size assessment methodology, leading to the surrogate threshold effect. These recent developments will be introduced briefly.

This Instant Short Course will present an overview of these developments, with illustrations predominantly from the fields of ophthalmology, oncology and mental health.


Topics covered in this Instant Short Course:

  • Single-trial framework: Introduction, Single-trial case. Duration: 1 hour 23 minutes.
  • Meta-analytic framework: Continuous meta-analytic framework, Extensions to other endpoints. Duration: 1 hour 11 minutes.
  • Extensions, unification and design: Surrogate endpoints in psychiatry, Longitudinal outcomes and unification, Design implications. Duration: 41 minutes.

Free preview

You need Flash Player 9 or later installed to play this s3video

Note: Load time will be affected by the speed of your Internet connection. A slow connection may cause a black warning message to be displayed across the video. If this happens, reload the web page by pressing F5 (Windows) or Command-R (Mac OS). If you experience other problems, check the minimum system requirements.

Live course

This Instant Short Course is based on a full-day live course which has been offered at the following meetings:

  • Spring Meeting of Eastern North American Region of the International Biometric Society, Austin, TX, 2005.
  • The Food and Drug Administration, Rockville, Maryland, 2005.
  • FDA/Industry Meeting, Washington DC, 2006.
  • Indiana Chapter of the American Statistical Association, Indianapolis, IN, 2007.
  • Biostatistics Section of the Belgian Statistical Society, Braine-l’Alleud, Belgium, 2007.
  • Royal Statistical Society, London, UK, 2007 and 2008.
  • American Statistical Association, LearnStat, 2008.
  • Deming Conference, Atlantic City, NJ, 2009.


Browse the catalog of Instant Conferences and Instant Short Courses.

© 2008-2017 Supremum Group. All Rights Reserved.
Supremum Group | Terms of Use | Privacy Policy | Contact