DEPARTMENT OF MEDICAL STATISTICS
DE MONTFORT UNIVERSITY, LEICESTER
Seminar Announcement
Time: Wednesday, 23rd June 1999, 1 p.m.
Place: James Went Building, DMU Leicester
Room JW 6-06
Speaker: Susan Todd
The Medical and Pharmaceutical Statistics Research
Unit,
Department of Applied Statistics, The University of
Reading
Title: Sequential monitoring of two endpoints in a clinical
trial
Abstract:
Consider a clinical trial designed to compare an experimental treatment
with a
control. To conduct the experiment sequentially requires a choice of
primary
patient response, definition of appropriate test statistics and a choice
of
stopping rule. When a single primary response is obtained from each
patient,
univariate stopping rules are appropriate. Once the trial has stopped,
valid
methods for determining significance, estimating parameters and setting
confidence limits are necessary. Methodology for the univariate case is
readily available.
In practice, situations arise when more than one response per patient is
of
interest. Examples include the use of a surrogate endpoint early in the
study
which is later replaced by a longer term outcome; simultaneous
monitoring of
efficacy and safety responses; and the need to demonstrate efficacy for
two
outcome measures to gain licensing. It is required that any decision to
stop
the study be based upon both these measures.
The special case of simultaneously monitoring one efficacy and one
safety
response has been considered by a number of authors. In this talk the
wider
range of problems mentioned above is discussed. Examples will be given
of the
form of designs in these potential applications, and issues of analysis
considered.
------------------------------------------------------------------------------
All welcome !
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|