I don't see any problem (unless the dummies are the panel fixed effects). However, can you provide full content of the results window?
Nicola
P.S. Please plain text e-mails and no attachments!
At 02.33 13/03/2008 -0400, Duha Al-Kuwari wrote:
>This is a multi-part message in MIME format.
>
>- --Boundary_(ID_HjYWiG9kQEBycUpXw4a/Vg)
>Content-type: text/plain
>Content-transfer-encoding: 7BIT
>Content-disposition: inline
>
>dear all, good morning
>
>i have a question about random effect probit model.
>
>is it an acceptable to include dummy variables in random effects model. i'm asking this question because i've got strange results when i added dummy variables to my model .
>
>that is , when i used random effects probit model to test my variables ( before adding dummy variables) as:
>
>xtprobit y x1 x2 x3 x4 x5 x6, i(id)
>mfx compute, predict (pu0)
>
>i've got significant results. however, when i added dummy variables to the model as:
>
>xtprobit y x1 x2 x3 x4 x5 x6 x7 d2 d3 d4 d5, i(id)
>mfx compute, predict (pu0)
>
>the results were strange: non of Z values were insignificant, except d3, moreover the Z values of variables wee almost the same . can any one please help me and tell me whether it is an acceptable to use random effect probit model
>
>thanks
>
[snip]
*
* 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/
