# st: RE: Estimating glm w/log and gaussian,was RE: transforming predictions from loglinear models

 From Miller.DavidJ@epamail.epa.gov To statalist@hsphsun2.harvard.edu Subject st: RE: Estimating glm w/log and gaussian,was RE: transforming predictions from loglinear models Date Wed, 31 Aug 2005 20:58:42 -0400

```Just a thought --

I might normally think that the semicolon appearing after  your command
line was the problem

For example, this works --

webuse  auto
glm mpg weight, noconstant link(log) fam(gauss) cluster(make)

Iteration 0:   log pseudolikelihood = -350.48236
Iteration 1:   log pseudolikelihood = -325.12147
Iteration 2:   log pseudolikelihood = -307.31936
Iteration 3:   log pseudolikelihood = -307.29842
Iteration 4:   log pseudolikelihood = -307.29839

Generalized linear models                          No. of obs      =
74
Optimization     : ML                              Residual df     =
73
Scale parameter =
240.1084
Deviance         =   17527.9143                    (1/df) Deviance =
240.1084
Pearson          =   17527.9143                    (1/df) Pearson  =
240.1084

Variance function: V(u) = 1                        [Gaussian]
Link function    : g(u) = ln(u)                    [Log]

AIC             =
8.332389
Log pseudolikelihood = -307.2983927                BIC             =
17213.72

(Std. Err. adjusted for 74 clusters in
make)
------------------------------------------------------------------------------
|               Robust
mpg |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
Interval]
-------------+----------------------------------------------------------------
weight |   .0007566   .0000298    25.43   0.000     .0006983
.0008149
------------------------------------------------------------------------------

But this doesn't :

. glm mpg weight, noconstant link(log) fam(gauss) cluster(make);
option ; not allowed
r(198);

But I note that  the Stata output here  does precisely identify the
problem as the semicolon  and this doesn't seem to be the case with your
output.  You might want to try taking out the semicolon and -- as Nick
suggests -- send the surrounding code.

david

David J. Miller, Chief
Chemistry & Exposure Branch
Health Effects Division
Office of Pesticide Programs
703-305-5352 (voice)
703 605-1289 (fax)

visit: http://www.epa.gov/pesticides/

*
*   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/
```