Ph.D. Studentship, October 2010 start:
>> Developing statistical methods for Randomized Controlled Trials <<
We would like to hear from prospective students who are keen to study for a
Ph.D. We have one three or four-year studentship joint funded by the MRC and
the University of Bristol, to allow the study of statistical methods in
randomized controlled trials.
The successful applicant will work within the MRC funded ConDuCT hub for
clinical trials methodology research, based within the new School of Social
and Community Medicine at the University of Bristol. The four-year
studentship allows a year of training in clinical trials research for a
recent graduate or a student moving from a different area of application.
Possible projects include two aimed at developing statistical methods in
economic evaluation:
[1] Optimising the statistical precision of economic evaluations conducted
alongside randomised controlled trials.
Supervisors: Dr Will Hollingworth & Dr Chris Metcalfe
Summary: The sample sizes of randomised controlled trials are almost always
based on achieving statistical power for comparisons of clinical outcome
rather than comparisons of cost-effectiveness. It is often assumed that
randomised controlled trials are severely underpowered on economic outcomes,
but there is little empirical evidence to substantiate this. Potential
elements of this project include a post hoc examination of statistical power
to detect an important difference in cost-effectiveness in published trials,
and a prospective study predicting statistical precision in
cost-effectiveness estimates based on pilot cost-effectiveness data.
[2] The net benefit regression framework for estimating cost effectiveness
in randomised controlled trials.
Supervisors: Dr Chris Metcalfe & Dr Will Hollingworth
Summary: Incremental net benefit is a measure of cost-effectiveness that can
be estimated using standard regression models. Consequently there is the
potential to take those statistical methods developed within the regression
framework and apply them to cost-effectiveness analysis. For example, it may
be possible to obtain an unbiased estimate of cost-effectiveness in those
patients who adhere to their allocated treatment, and to obtain accurate
standard errors for data collected in cluster randomised trials.
For more details and the application procedure please see the ConDuCT Ph.D.
programme prospectus, available under “Other funding opportunities” on our
postgraduate opportunities web page:
<http://www.epi.bris.ac.uk/postgrad/pg.htm>
Please get your application to us by Tuesday 30th March to ensure an October
2010 start. Later applications will be considered if the studentship is
still available.
--------------------------------------
Chris Metcalfe PhD
Senior Lecturer in Medical Statistics
Department of Social Medicine
University of Bristol
Canynge Hall
39 Whatley Road
Bristol
United Kingdom
BS8 2PS
T: +44(0)117 928 7326
F: +44(0)117 928 7325
E: [log in to unmask]
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|