--- Arne Mastekaasa wrote:
> I know how to access coefficient estimates in postestimation commands
> such as -test-, but I've not been able to find out how to do this with
> estimated variance parameters, e.g. from -xtmixed-.
These are typically stored in the vector of parameters e(b). I
never remember the equation name under which they are stored so
I always first use -matrix list e(b)- to see the entire vector
with names and than figure out which parameter I need. One more
tricky thing is that Stata typically doesn't maximize the
likelihood with respect to the standard deviation (which is
bounded to be larger then zero) but with respect to
ln(standard deviation) (which ranges between -infinity and
+infinity). See the example below:
*----------- begin example -------------
use http://www.stata-press.com/data/r9/pig.dta, clear
xtmixed weight week || id:
matrix list e(b)
di as txt "sd of _cons is " as result exp([lns1_1_1]_b[_cons])
di as txt "var of _cons is " as result exp([lns1_1_1]_b[_cons])^2
*------------ end example --------------
(For more on how to use examples I sent to the Statalist, see
http://home.fsw.vu.nl/m.buis/stata/exampleFAQ.html
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
