REMINDER
CENTRE FOR MEDICAL STATISTICS
SEMINAR SERIES on BIOSTATISTICS 2000/2001
NO 7: Wednesday, May 9th, 2001, at 2:30 pm
"How biased are the results of non-randomised studies, and can we do
anything about it?"
Jon Deeks
(Institute of Health Sciences,
University of Oxford)
Non-randomised evaluations of healthcare interventions are considered
less reliable than randomised comparisons as they
are subject to selection biases, but the degree to which they may be
biased is unknown. This hinders the interpretation of
both individual non-randomised studies and systematic reviews of
non-randomised studies. Many non-randomised studies
utilise regression models to adjust for differences in case-mix and
correct for selection bias, but the ability of the models to
make correct adjustments has rarely been investigated. We have
investigated distributions of bias associated with con-
current and historical cohort designs using data from large multi-centre
trials, and have evaluated the ability of commonly
used statistical methods of case-mix adjustment to control for the
observed biases. Our findings are of importance to all
who are undertaking or reviewing evaluations of the clinical effects of
health care interventions.
All welcome!!
Venue:
Room 2.22, Third Floor
The MacKay Building
Keele University
http://www.keele.ac.uk
http://www.keele.ac.uk/depts/ma/seminars/medstats.html
http://www.keele.ac.uk/university/campus/maps/
___________________________________________
Janet Drewery
Secretary
Centre for Medical Statistics
Keele University
Staffordshire ST5 5BG
England
Email: [log in to unmask]
Tel: (01782) 583269
Fax: (01782) 583269/584268
|