Please find below information about the next Royal Statistical Society Manchester Local Group meeting being held tomorrow.
---------------------------------------
Date: Wednesday 11th May 2011
Time: 16.00 - 17.00
Venue: G.107 Alan Turing Building, Oxford Road, The University of Manchester
Dr Richard Riley
School of Mathematics, University of Birmingham
"Individual participant data meta-analysis of prognostic factor studies: state of the art?"
Joint work with Ghada Abo-Zaid and Willi Sauerbrei
Abstract:
Prognostic factors are associated with the risk of a subsequent outcome in people with a given disease or health condition. They have a broad array of uses in clinical practice and healthcare research. For example, prognostic factors help define disease at diagnosis; they inform treatment strategies for individual patients; they may be causal for disease outcome; and they inform randomisation strategies in clinical trials. Research to identify factors that are truly prognostic is abundant in the medical literature, and meta-analysis is needed to combine multiple prognostic factor studies and produce evidence-based prognostic factor results.
Meta-analysis using individual participant data (IPD), where the raw data are synthesised from multiple studies, has been championed as the gold-standard for synthesising prognostic factor studies. In this talk I will examine the feasibility and conduct of this approach, using a systematic review of currently published IPD meta-analyses of prognostic factors studies. I will show that availability of IPD offers many advantages, such as checking modelling assumptions; analysing variables on their continuous scale with the possibility to assess non-linear relationships; and obtaining results adjusted for other variables. However, researchers also faced many challenges, such as large cost and time required to obtain and clean IPD; unavailable IPD for some studies; different sets of prognostic factors in each study; and variability in study methods of measurement. I will conclude with suggestions for where improvements are needed in current IPD meta-analyses; in particular, continuous variables are often categorised without reason; publication bias and availability bias are rarely examined; and reporting standards are often sub-standard.
Tea/Coffee and Biscuits will be served from 15.30 on the first floor Atrium Bridge
All are welcome to attend.
For more information, please visit: http://www.rss-manchester.org/2010-11_session.html
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|