Is your Stata up-to-date?
. which xtmixed
C:\Program Files\Stata9\ado\updates\x\xtmixed.ado
*! version 1.1.8 17aug2005
. which statsby
C:\Program Files\Stata9\ado\updates\s\statsby.ado
*! version 3.2.6 19aug2005
This example works ok:
. use http://www.stata-press.com/data/r9/productivity.dta, clear
(Public Capital Productivity)
. gen byte tag = year<1978
. statsby _b , clear total verbose by(tag): xtmixed gsp ///
> ||region: ||state: ||year: if year >1971 ,difficult
(running xtmixed on estimation sample)
command: xtmixed (gsp) (region:) (state:) (year: if year >1971,
difficult)
gsp_b_cons: [gsp]_b[_cons]
lns1_1_1_b_~s: [lns1_1_1]_b[_cons]
lns2_1_1_b_~s: [lns2_1_1]_b[_cons]
lns3_1_1_b_~s: [lns3_1_1]_b[_cons]
lnsig_e_b_c~s: [lnsig_e]_b[_cons]
by: tag
Statsby groups
----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5
..
. l, noobs
+----------------------------------------------------------------+
| tag gsp_b_~s lns1_1_~s lns2_1_~s lns3_1_~s lnsig_e~s |
|----------------------------------------------------------------|
| 0 10.77133 -.3787023 -.2424748 -2.832074 -2.871997 |
| 1 10.57808 -.2984414 -.2535143 -3.284717 -3.153928 |
| . 10.69417 -.3458418 -.2483991 -2.241496 -2.493095 |
+----------------------------------------------------------------+
You might try contacting tech-support:
http://www.stata.com/support/faqs/techsup/techsup.html
Scott
> -----Original Message-----
> From: [email protected] [mailto:owner-
> [email protected]] On Behalf Of Rory Wolfe
> Sent: Wednesday, March 08, 2006 8:14 PM
> To: [email protected]
> Subject: st: Re: Non standard commands and statsby
>
> I encountered the problem in a three-level model (output further down):
> statsby _b, clear by(cycle): xtmixed angle || pt: || session: if
> side=="L", mle
>
> and I've tried cutting it down to a two-level model as in Scott's example
> but haven't had any success with that either (same problem as for the
> above).
>
> If I cut it down to a 1-level model, i.e. remove all random effects, then
> it runs ok:
> statsby _b, clear by(cycle): xtmixed angle if side=="L", mle
>
> Here is the full error output from statsby
>
> . statsby _b , clear noisily by(cycle):xtmixed angle ||pt: ||session: if
> side=="L", mle
> statsby: First call to xtmixed with data as is:
>
> . xtmixed angle ||pt: ||session: if side=="L", mle
> invalid ':'
>
> ...
>
> The -xtmixed- syntax for my 3-level model, i.e. what statsby tries to
> run above but complains about an "invalid ':'", works fine when I run
> it without -statsby- !!!
>
> Rory
>
*
* 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/
