Ooops, I found a typo. I meant to say "level-1" units (not level-2).
Hi Daniel,
I think what you want to model is sometimes called a cross-classified
random effects model and as far as I know this is not possible with
Stata, not even with -gllamm-. However, HLM will do it. Check this link
and look ad the HCM2 model:
http://www.ssicentral.com/hlm/hlm6/hlm6.htm.
I have never tried such a model myself but the textbook example is
about students cross-classified by classrooms and neighbourhoods. I
think this model can be adapted to your problem with your level-1 units
cross-classified by country and time period.
The bad news is that you have to spend money on the HLM software ( I
think other multilevel packages might handle this problem also e.g.
MlWin and Mplus but I have not checked that). Unfortunately, Sean
Reardon's excellent package -hlm- that is download-able from SSC,
currently only support HLM2 and HLM3 models but not HCM2 so you have to
leave the Stata environment to run your models.
That's my 2 cents. I hope it helped.
Michael
On 2005-02-28, at 18:01, daniel perez wrote:
Hi everybody,
I hope I'll find somebody which is able to get
through a specification problem with panel data.
I want to compute a two-way random a model like this
one:
yi,t= a0+consi+const+ b1Xi,t+epsiloni,t
where a0 is a common constant and consi is a
country specific constant and const is a specific time
constant.
I used xtreg y x dummy (for time period),re i(country)
but I'm not sure that it's the correct way
to formulate this two-way model under random effects
approach...
Thank in advance for any help
Daniel
D�couvrez le nouveau Yahoo! Mail : 250 Mo d'espace de stockage pour
vos mails !
Cr�ez votre Yahoo! Mail sur http://fr.mail.yahoo.com/
*
* 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/
------------------------------------------------
Michael Ingre , PhD student & Research Associate
Department of Psychology, Stockholm University &
National Institute for Psychosocial Medicine IPM
Box 230, 171 77 Stockholm, Sweden
*
* 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/
