Please see details below
Apologies for short notice
Royal Statistical Society Merseyside Local Group
Wednesday 16th April 2008 3.00pm
(Tea & Coffee afterwards)
Venue : Penthouse, Maths & Oceanography building University of Liverpool
Please contact Ashley Jones ([log in to unmask]) for further details.
---------------------------
Ian White MRC - Biostatistics Unit
Allowing for non-departures from randomised treatment in clinical trials.
Abstract:
In randomised trials with departures from allocated treatment, it may be
desirable to estimate the causal effect of treatment itself.
Intention-to-treat analysis does not do this: instead it provides an
unbiased comparison of treatment policies as implemented. Per-protocol
analysis is the most commonly used alternative in clinical trials, but it
can suffer from large selection bias. Randomisation-based methods of causal
inference avoid both these problems. I will describe these methods and give
some examples where they have given useful conclusions.
|