Hi!!
Maybe this question has been asked before or it's very trivial, but
it's been a real nightmare to me to try to find out the answer!
I am performing an estimation of a migration equation using
xtreg y x1...xn, re i(id_obs) robust cluster(id_obs)
My question is:
how does STATA calculates the degrees of freedom of the Wald Chi2
test? I have a lot of observations (more than 30000), around 2000
groups and 15 T (even if it is an unbalanced panel because I have some
zeros).
The more regressors I use, the more dof the model seems to have, and I
don't know why!!
I give you two examples to clarify...
Any suggestions will be great!
Thanks in advance,
--
Rosa Sanchis-Guarner Herrero
-----------------
An�lisi Quantitativa Regional (AQR) Research Group-IREA
Departament d'Econometria, Estad�stica i Economia Espanyola
Facultat de Ci�ncies Econ�miques i Empresarials
Universitat de Barcelona
Avd. Diagonal, 690, Torre IV, 08034 Barcelona
tel: +34 934021011, Fax: +34 934021821
email: [email protected]
"When life gives you lemons, sometimes you can make lemonade" John C.Baez
*
* 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/
