I'd be typically more interested in doing random-effects meta
analysis
and I haven't got Stata 9 yet, so I can only really guess, but
perhaps
the new mixed models capabilities will be of some help here?
I'm not quite sure how the overall effect and variance estimates from
the meta-analysis commands might compare to those available from the
new functions, and I appreciate that's crucial (!), but in principle
is
this goodbye to meta, metan, metareg etc? Random-effects analysis to
be
handled by mixed models commands, graphics to be handled by Roger
Newson's portfolio of commands.
It would be useful to hear from people who've tried out the new
commands.
Dominic Muston.
*
* 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/
