Adaptive Designs and Multiple Testing Procedures for Clinical Trials

Clinical trials are the gold standard study design for assessing the efficacy and safety of an intervention. Adaptive designs are a novel approach to improving the efficiency and ethical properties of clinical trials. With an adaptive design, information gathered during the trial can be used to change the design in a statistically robust way. There are many types of adaptive designs that are possible for different situations ranging from phase I to phase III.  In both adaptive and non-adaptive trials, there are often multiple hypotheses being tested. Examples include trials with multiple endpoints, multiple treatment arms and when a trial tests a treatment in different patient subgroups. Adaptive trials often mean that a particular hypothesis is tested several times during the trial. This creates issues with multiple testing, for which suitable procedures are needed to ensure the appropriate error rate is controlled.

In this course we will give an overview of multiple testing issues and adaptive designs in trials. Participants will learn about a variety of new adaptive clinical trial designs, including multi-arm multi-stage (MAMS), umbrella studies and adaptive randomisation. As well as learning about how to design adaptive trials we will cover the implications of the design on the analysis and practical aspects of running the trial.

Throughout the course, real examples will be used to demonstrate the methodology. There will be a strong emphasis on learning how to use available software (in both R and Stata depending on the preference of the delegate) to implement the methodology in practice.

Course Tutors

Dr Michael Grayling, Newcastle University
Professor Adrian Mander, Cardiff University
Dr David Robertson, MRC Biostatistics Unit
Professor James Wason, MRC Biostatistics Unit and Newcastle University

Intended Audience

The course is aimed at statisticians, although non-statisticians with strong quantitative experience would benefit from the course also.

Prerequisites

Knowledge of standard statistical methods fordesign and analysis of randomised clinical trials is assumed.

Computing Practicals

Participants will gain most from the practicals if they have a working knowledge of either R or Stata, and bring a laptop with R or Stata loaded.

Course Objectives

After the course, participants will be aware of a broad range of adaptive designs that are available and be able to design some of their own using available software.

Software Download

Details of software to be downloaded for use on the course practicals will be given to course participants.

For further course details or information please visit  http://www.mrc-bsu.cam.ac.uk/training/short-courses/

Registration

To register for this course, please click here

Course Enquiries

For answers to course queries, please email courseadmin@mrc-bsu.cam.ac.uk