Mayer Brezis wrote:
> Can anyone give me one or more good example(s) of a well done large RCT
> reaching a conclusion contradictory to a well done meta-analysis (including
> this RCT) and what are the potential or likely explanations for those
> discrepancies?
The explanation that I offer is that a meta-analysis is like a
multi-center trial where each center uses its own protocol and some
centers fail to share their results.
The classic reference is actually a meta-analysis of meta-analyses:
Jacques LeLorier, Genevieve Gregoire, Abdeltif Benhaddad, Julie
Lapierre, Francois Derderian. Discrepancies between Meta-Analyses and
Subsequent Large Randomized, Controlled Trials. N Engl J Med.
1997;337(8):536-542.
The full free text is available on the web. If you have trouble finding
this article, look up the link on my page:
http://www.pmean.com/category/SystematicOverviews.html
--
Steve Simon, Standard Disclaimer
Second free statistics webinar, Wed, Nov 4, 11am-noon CST.
"The first three steps in data entry, with examples in PASW/SPSS"
Details at www.pmean.com/webinars
|