Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: estimating random effects in panel probit models


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: estimating random effects in panel probit models
Date   Mon, 26 May 2008 16:57:07 +0100

-gllamm- is telling you that it is finding it difficult to maximise the likelihood for your model. You need to rethink your model or consider what characteristics of your data might be problematic. 

Nick
n.j.cox@durham.ac.uk 

Saygin Sahinöz

I have a panel of sectoral data (20 sectors) for 18 years (quarterly). I
want to run random effects probit model using gllamm. I first defined 2
equations for random effects
gen byte one = 1
eq cons : one
eq ihr : ihr

and then use

"gllamm state imp, i(sektor) family(binomial) nrf(2) nip(30) eqs(ihr cons)
link(probit) adapt"
However, I received the message "numerical derivatives are approximate flat
or discontinuous region encountered". What may be the reason of this
message??

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index