Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Meta-analysis pooling relative risk from relative risks possible?


From   David Hoaglin <dchoaglin@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Meta-analysis pooling relative risk from relative risks possible?
Date   Thu, 16 Feb 2012 07:31:16 -0500

Do the relative risks reported by the individual studies come from
their respective 2x2 tables, or are they adjusted?  If they
incorporate adjustments, and the variables used in the adjustments
differ among studies, the relative risks are not comparable.

Although it is customary to weight the studies' estimates proportional
to the reciprocal of the estimated variance, bias can result, even in
fixed-effect meta-analysis.  The books and software generally give no
warning that using the estimated variances as if they were the known
true variances can cause such problems.  If you had the counts in the
cells of the 2x2s, you could try a Bayesian approach.

David Hoaglin

On Thu, Feb 16, 2012 at 3:13 AM, Sofia Ramiro <sofiaramiro@hotmail.com> wrote:
>
> Dear all,
>
> I would like to ask your help for the following: I would like to perform a meta-analysis of some studies. However, I do not have the raw data to fill in the 2X2 table. I have a Relative Risk (and correspondent 95%CI) for each study. Is it possible to pool these RR and get a pooled estimate? If yes, how?
> I have been searching online for this information, but haven't been successful...

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index