Statalist The Stata Listserver


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

st: Re: inicial values not feasible


From   "Rodrigo Alfaro" <ralfaro76@hotmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: inicial values not feasible
Date   Thu, 30 Mar 2006 16:47:17 -0500

Maybe there is problem with the variable x, y and z.

Take a look of the correlations of these variables:

biprobit (a = b c d) (t = y z) if x!=.
corr x y z if e(sample)

Rodrigo.

----- Original Message ----- From: "Avcharian, Alexis" <avcharian@ort.edu.uy>
To: "stata" <statalist@hsphsun2.harvard.edu>
Sent: Thursday, March 30, 2006 4:10 PM
Subject: st: inicial values not feasible



I estimated a biprobit model and stata said:

inicial values not feasible

I tried different estimations and realized that the "inicial values not feasible" problem only occured when i include variable x in the estimation.
i.e.:
biprobit (a = b c d)(t = x y z) inicial values not feasible

If I don't include x, stata does the regression.
It even works when I include x in the first equation (a= b c d x)(t= y z)
Since x is a very important variable I have to include it in (t= x y z), so dropping it is not an option.
Can anyone please give me some advice.
Thanks in advance.
Alexis






*
* 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/

*
*   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 1996–2020 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index