Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# Re: st: xtmixed with nonrtolerance. What happens?

 From "Lukas Bösch" To statalist@hsphsun2.harvard.edu Subject Re: st: xtmixed with nonrtolerance. What happens? Date Fri, 24 Jun 2011 12:11:17 +0200

```One more information:

When i run the modell only with the complete export time series. Without any zeroes in the dependent data, the output looks like this:

. xtmixed centquantity2 centyear2 centforestarea2 centgdp2 centlandarea2 centpopulation2 || _all: R.country || _all: R.genus

Performing EM optimization:

Iteration 0:   log restricted-likelihood = -1907.9114
numerical derivatives are approximate
nearby values are missing
Iteration 1:   log restricted-likelihood = -1906.3037
numerical derivatives are approximate
nearby values are missing
Iteration 2:   log restricted-likelihood = -1906.3037

Computing standard errors:

Mixed-effects REML regression                   Number of obs      =      1216
Group variable: _all                            Number of groups   =         1

Obs per group: min =      1216
avg =    1216.0
max =      1216

Wald chi2(5)       =     21.29
Log restricted-likelihood = -1906.3037          Prob > chi2        =    0.0007

centquanti~2 |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
centyear2 |  -.1372919   .0456083    -3.01   0.003    -.2266825   -.0479014
centfores~a2 |  -.7787292   .3464103    -2.25   0.025    -1.457681   -.0997774
centgdp2 |  -1.510474   1.005607    -1.50   0.133    -3.481427    .4604796
centlandar~2 |  -.5532811   .8824918    -0.63   0.531    -2.282933    1.176371
centpopul~n2 |   1.116585   .9528179     1.17   0.241    -.7509036    2.984074
_cons |   .5183642   .8785702     0.59   0.555    -1.203602     2.24033

Random-effects Parameters  |   Estimate   Std. Err.     [95% Conf. Interval]
_all: Identity               |
sd(R.country) |   3.484453   .5512833       2.55543     4.75122
_all: Identity               |
sd(R.genus) |   2.93e-06   .0221629             0
sd(Residual) |   1.100754   .0225709      1.057393    1.145893

LR test vs. linear regression:       chi2(2) =  1333.21   Prob > chi2 = 0.0000
Note: LR test is conservative and provided only for reference.

Still not perfect, but it seems to work better

--
NEU: FreePhone - kostenlos mobil telefonieren!
Jetzt informieren: http://www.gmx.net/de/go/freephone
*
*   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/
```