st: meta -regression: comparing semi-log and level-level models

[thushyanthan baskaran <thushyanthan.baskaran@awi.uni-heidelberg.de>]

Dear Statalisters,

I would like to conduct a meta-analysis (in economics) and have a 
question regarding the methodology. In the literature I am concerned 
with, coefficents have been estimated using level-level, semi-log and 
log-log models. Obviously, the interpretation of the effect varies 
according to the model used, and I find it hard to see how the "true" 
strangth of the effect can be derived.  Now: Is it possible to compare 
these different coefficents by some kind of transformation, and to 
calculate some kind of "average" effect?

Thanks in advance

Thushyanthan

*
*   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/