University of Newcastle upon Tyne

School of Mathematics and Statistics

Statistics Seminars 2005-2006

14 October 2005, L401, 2:15pm

Professor John Lewis

Will my new tablets be as good as the old ones, doctor?

 Abstract

On 27^th July 2005 the European Medicines Agency (EMEA) issued a new European “Guideline on the choice of the non-inferiority margin” (EMEA /CPMP /EWP /2158 /99), an event which could easily pass by unnoticed – and you may even think that it should. The document is about clinical trials that are intended to show that two medical treatments are similar in effect, or that one of them is not markedly worse than the other. In particular it provides advice on the size of difference that such trials should be trying to detect.

This is the latest chapter in a long story relating to such trials. Special pharmaceutical and regulatory attention has been paid to equivalence and non-inferiority trials since at least the 1970s, beginning with bio-equivalence trials. The statistical and related practical problems associated with these trials, although appearing on the surface to be fairly trivial, turn out to be difficult to solve, especially for major pragmatic clinical trials. Attempts to reach international agreements on their design and analysis have not been easy or conclusive. There are ethical implications that led to an international outcry when the Declaration of Helsinki was updated. There are also implications for the high standards of conduct and record-keeping required in controlled trials, leading to increased costs and accusations of unnecessary delays and disruption to valuable medical research.

 The seminar will describe the history of these events, with examples of real medical situations that have proved problematic. The current status of the issues relating to equivalence and non-inferiority trials will be explained, including the most recent regulatory guidance.

Return to timetable for 2005-06 seminars

School of Mathematics and Statistics Homepage