Hello,
Thank you, Bobby.
I apprecaite your help.
Sincerely,
Satomi
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Roberto G. Gutierrez, StataCorp
Sent: Friday, March 28, 2008 2:12 PM
To: [email protected]
Subject: Re: st: Running an empty model using xtmixed
Satomi Yamamoto <[email protected]> asks:
> Could I use the xtmixed command to run a null model? I used the
> pig.dta data (http://www.stata-press.com/data/r10/pig.dta) and run
> xtmixed weight||id:, var
> But, I was not able to converge the data:
[...]
> Is there another way of running the intercept only model in Stata?
> Or, did I forget to include options in xtmixed? It would be great if
> somebody could help me wit this.
There is nothing that states you can't fit a null model with -xtmixed-, and the syntax you use is the correct one. It is just that in your particular case -xtmixed- failed to converge, most likely because of a near-zero variance component at the -id- level.
. sysuse auto, clear
. xtmixed mpg || rep78:
does converge. In fact, you can even be more "null" and do
. xtmixed mpg
or if you want to get really crazy
. xtmixed mpg, nocons
--Bobby
[email protected]
*
* 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/
