Statalist The Stata Listserver


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

st: Re: xttobit with no feasible values


From   "Rodrigo A. Alfaro" <raalfaroa@gmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: xttobit with no feasible values
Date   Tue, 29 May 2007 16:55:40 -0400

Possible problems

(1) The usual, update your Stata. -update query-
(2) Your initial parameters are infeasible, in particular 0.1
You can change that number or trying fitting with -areg-
(3) You linear model drops some variables, then
you don't have the same dimension in b0
(4) Your model is hard to fit then you shoudl try
-xttobit- but change the quadrature points, maybe you
model does not fit the theoretical assumptions.

R


----- Original Message ----- From: "Leonor Saravia" <lmisaravia@gmail.com>
To: <statalist@hsphsun2.harvard.edu>
Sent: Tuesday, May 29, 2007 4:26 PM
Subject: st: xttobit with no feasible values



Hello,

I was trying to run a xttobit programm in Stata (using Stata 9) but it
doesn't worked, in fact, it runs many hours and didn't converge to
anything. So, now I'm trying to run the same programm (xttobit) but
defining the initial values for the coefficients. To do this, I used
the guide that David Drucker did
(http://www.stata.com/statalist/archive/2003-05/msg00650.html). My
problem is that when I run the programm Stata tells me that the
initial values are not feasible when runs the xttobit. Please, if
someone knows what's happening or how to solve the problem in other
way I'd appreciated very much.

What I did:

First: I've estimated my model by OLS

reg inversion98 tau region1-region12 EMBI industria1-industria8 DumIE
desemp_r tam_emp1 tam_emp2

Second: Generate the matrix of initial values

matrix b0=e(b), ln(e(rmse)^2),.1
matrix list b0

Third: Run the random effects Tobit, using the "new" initial coefficients.

xttobit inversion98 tau region1-region12 EMBI industria1-industria8
DumIE desemp_r tam_emp1 tam_emp2, ll(0) from(b0, copy)


Well, thank you very much for your time.

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