st: xttobit

 From "naceur khraief" <[email protected]> To [email protected] Subject st: xttobit Date Wed, 01 Dec 2004 12:52:36 -0500

Dear statalisters

I am running xttobit estimator. I tried different numbers of quadrature
points (4, 8, 12..30) but I had the same problem. I am not sure that the
estimates are robust. Convergence achived after 4 iterations, I get s.e
for sigma_e but not for sigma_u and 0 for rho.
In other side to use the adaptive quadrature I want to get a starting
values from xttobit ( sigma_u and sigma_e). It's not possible because
sigma_u equal 0.
Best regards,

.xttobit Dlnq DlnQ Dlnreau lnreus lnremq lnresk lnrehk lnrejp ,
i(country) ll(0)

Obtaining starting values for full model:

Iteration 0: log likelihood = -2386.4927
Iteration 1: log likelihood = -2386.4786

Fitting full model:

Iteration 0: log likelihood = -1566.5403
Iteration 1: log likelihood = -1513.6376
Iteration 2: log likelihood = -1508.7207
Iteration 3: log likelihood = -1508.5333
Iteration 4: log likelihood = -1508.533

Random-effects tobit regression Number of obs = 1140
Group variable (i): country Number of groups = 6

Random effects u_i ~ Gaussian Obs per group: min= 190
avg = 190.0
max = 190

Wald chi2(7) = 13.18
Log likelihood = -1508.533 Prob > chi2 = 0.0678

-------------------------------------------------------------------------
-----
Dlnq | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+-----------------------------------------------------------
-----
DlnQ | .1693858 .4303348 0.39 0.694 -.6740549
1.012827
Dlnreau | 1.116371 2.814282 0.40 0.692 -4.39952
6.632263
lnreus | .1485542 1.444226 0.10 0.918 -2.682078
2.979186
lnremq | -1.558281 .7213964 -2.16 0.031 -2.972192 -
.1443697
lnresk | .7600745 .8181918 0.93 0.353 -.8435519
2.363701
lnrehk | 1.008161 .8777873 1.15 0.251 -.7122704
2.728593
lnrejp | -1.124204 .7599142 -1.48 0.139 -
2.613609 .3652
_cons | -4.554228 4.062599 -1.12 0.262 -12.51678
3.40832
-------------+---------------------------------------------------------
sigma_u 0 . . . .
sigma_e 2.204545 .0713254 30.91 0.000 2.064749 2.34434
-------------+-----------------------------------------------------------
rho | 0 . . .
-------------------------------------------------------------------------

Observation summary: 529 uncensored observations
611 left-censored observations
0 right-censored observations

_________________________________________________________________
Balayez vos courriels entrants et sortants et les pi�ces jointes et contribuez � �liminer les virus destructeurs susceptibles d�y �tre int�gr�s. http://join.msn.com/?pgmarket=fr-ca&page=features/virus Commencez d�s maintenant � profiter de tous les avantages de MSN Premium et obtenez les deux premiers mois GRATUITS*.

*
* 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/