Gerben - Where do these risk ratios come from? Are they estimated from
prospective studies, or are they somehow obtained from retrospective studies
with independent estimates of incidence rates, or are they assumed equal to
odds ratios because the incidence rate is very small? Depending on how you
obtained these risk ratios, you should be able to formulate a precise
regression and error model. Without knowing what this model is, it's hard to
say whether Stata has built in routines for estimating it.
Al Feiveson
-----Original Message-----
From: G. ter Riet [mailto:[email protected]]
Sent: Wednesday, May 21, 2003 9:45 AM
To: [email protected]
Subject: st: regression dilution bias: Stata instead of BUGS?
Dear List Members,
I'd like to perform regression analyses in the context of a meta-
analysis. The dependent variable is the relative risk (RR) and the
independent variable the event rate in the placebo groups. Who could
direct me to the correct commands in Stata (or do-files) to analyse
such data while avoiding spurious associations due to regression
dilution bias caused by regression of y-x on x?
Gerben ter Riet, MD PhD, Academic Medical Center
Dept. General Practice, Room J3-354, 1105 AZ Amsterdam
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
