Re: st: reference meta-analysis adjusted OR

[Marcos Vinicius <bioestatistico@inbox.com>]

Good point - thanks David very helpul.



> -----Original Message-----
> From: dchoaglin@gmail.com
> Sent: Fri, 25 Oct 2013 13:54:40 -0400
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: reference meta-analysis adjusted OR
> 
> Hi, Vinicius.
> 
> I can't give you a reference at present.  A meta-analysis of adjusted
> odds ratios may face a fundamental challenge: if adjusted odds ratios
> reported by individual studies have not been adjusted for the same set
> of covariates (defined and measured in the same or closely similar
> ways), then those adjusted odds ratios are generally not comparable.
> I assume that an adjusted odds ratio comes from a logistic regression
> model.  As in any regression model, the definition of the coefficient
> of each predictor includes the list of other predictors in the model.
> Thus, using different sets of covariates will produce adjusted odds
> ratios whose definitions are different.
> 
> David Hoaglin
> 
> On Fri, Oct 25, 2013 at 9:07 AM, Marcos Vinicius
> <bioestatistico@inbox.com> wrote:
>> I am looking for references for the subject  meta-analysis of adjusted
>> OR.
>> Any help would be very much appreciated.
>> Thanks,
>> Vinicius.
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/

____________________________________________________________
FREE 3D EARTH SCREENSAVER - Watch the Earth right on your desktop!
Check it out at http://www.inbox.com/earth



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