Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: nonconvergence of switching probit when data weighted


From   "Paula Albuquerque" <pcma@iseg.utl.pt>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: nonconvergence of switching probit when data weighted
Date   Thu, 12 Mar 2009 15:14:25 -0000

Dear Maarten,

I tried init() but it is also not allowed. As the same covariate can be in more than one equation, it would have to be possible so specify that the initial value was referring to the coefficient of this variable in this equation...

My dependent variables have: one of them) 40% of zeros and 60% of ones; the other) 67% of zeros and 37% of ones.

Paula

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Maarten buis
Sent: quinta-feira, 12 de Março de 2009 14:43
To: statalist@hsphsun2.harvard.edu
Subject: RE: st: nonconvergence of switching probit when data weighted


--- On Thu, 12/3/09, Paula Albuquerque wrote:
> I tried, but Stata replied that the option
> "from()" was not allowed with movestay... Is there
> any other way of doing it?

Yes, sometimes you can specify initial values with 
the -init()- option.

Are any of your dependent variables very unequally 
distributed? I already commented on your sample size, 
which is a bit small for a model like -movestay-, 
but if any of the dependent variables are very 
unequally distributed, then this becomes a much more
serious problem.

-- Maarten

-----------------------------------------




*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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