Joint Medical Section / Merseyside Local Group
Wednesday 12th November 2003 at 3pm, University of Liverpool (Lecture
Theatre C, University Science Lecture Building)
DOUGLAS G ALTMAN, Centre for Statistics in Medicine, Oxford
Randomised trials should be reported fully and accurately
Biased results from randomised trials can mislead decision-making in health
care at all levels. Critical appraisal of the quality of clinical trials is
thus essential, both for individual trials and within systematic reviews.
RCTs are often not reported adequately, hindering proper assessment of
their methodological quality. The CONSORT recommendations have been widely
supported but have as yet led to only modest improvement. I will present
evidence of the widespread poor methodological quality and poor reporting
of published trials, including recent findings on selective reporting.
Among other implications, I will argue that all trial protocols should be
published.
MARTIN BLAND, University of York
Cluster randomised trials in the medical literature
If a cluster-randomised trial is analysed without recognition of the
clustering, the analysis will ignore the possible correlation between
members of the same cluster. When positively correlated observations are
treated as independent, the result may be standard errors which are too
large, confidence intervals which are too narrow, and P values which are
too small, leading to conclusions which may be false. I shall describe the
analysis of some published trials and give a biased and partial review of
the history and current situation.
Please contact Catrin Tudur Smith ([log in to unmask]) for further
details.
---------- End Forwarded Message ----------
|