The following seminar will take place at the Department of Epidemiology and
Public Health, University of Leicester, 22-28 Princess Road West on thursday
11th November at 16:30 in room G20.
Details of how to get to the department can be found at
http://www.prw.le.ac.uk/epidemio/direct/
Thursday 11th November: 16:30
"Meta-analysis of ordinal outcomes" - abstract below
Rumana Omar (Imperial College)
META-ANALYSIS OF ORDINAL OUTCOMES
Rumana Z Omar
ABSTRACT
Meta-analyses are being undertaken in an increasing diversity of diseases and
conditions, some of which involve outcomes measured on an ordered categorical
scale. We consider methodology for undertaking a meta-analysis on individual
patient data for an ordinal response. The approach is based on the proportional
odds model, in which the treatment difference is represented by the log-odds
ratio. A general framework is considered for fixed and random effect models.
Tests of the validity of the various assumptions made in the meta-analysis
models, such as a global test of the assumption of proportional odds between
treatments, are considered. These models for meta-analysis can be extended to
handle the situation when the outcome variable has been classified to different
ordered categories in each study. Additionally, study-level and individual-level
covariates can also be included in analyses exploring potential sources of
heterogeneity. Both fixed and random effect models are illustrated on two
datasets, based on a classical approach using SAS and MLN and a Bayesian
approach using BUGS. The relative merits of the three software packages for such
meta-analyses are discussed. Comparison is made with a stratified summary
statistic approach for analysing ordinal data (Whitehead and Jones, 1994).
References
Whitehead A and Jones NMB (1994). A meta-analysis of clinical trials involving
different classifications of response into ordered categories, Statistics in
Medicine, 13, 2503-2515.
--
---------------------------------------------------------------------------
Paul Lambert
Dept Epidemiology and Public Health
University of Leicester
22-28 Princess Road West
Leicester
LE1 6TP
UK
Tel: (0116) 252 5407
Fax: +44 116 252 3272
e-mail:[log in to unmask]
---------------------------------------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|