# st: parmby with logistic command

 From "Cram, Peter" To statalist@hsphsun2.harvard.edu Subject st: parmby with logistic command Date Sun, 27 Oct 2002 13:20:32 -0600

```Statalist,

I have been using the parmby command to extract specific parameter
estimation results from some regressions i have been running:

With the regress command, parmby extracts all of the parameters that i
require quite nicely:

parmby "xi: regress ln_los wkend i.race i.sex id chf arythm valve pulmcirc
perivasc para neuro chrnlung dm dmcx hypothy renlfail liver ulcer aids lymph
mets tumor arth coag obese wghtloss lytes bldloss anemdef alcohol drug psych
depress htn_c, robust", saving(drg`drg'Coeff.dta, replace)idstr(`drg')
}

yields the following:

Regression with robust standard errors                 Number of obs ={res}
57508
{txt}F( 37, 57470)
={res}  103.91
{txt}Prob > F      =
{res} 0.0000
{txt}R-squared     =
{res} 0.0614
{txt}Root MSE      =
{res} .75152

{txt}{hline 13}{c TT}{hline 64}
{c |}               Robust
ln_los {c |}      Coef.   Std. Err.      t    P>|t|     [95% Conf.
Interval]
{hline 13}{char +}{hline 64}
wkend {c |}  {res} .0817493   .0068626    11.91   0.000     .0682985
.0952002
{txt}    _Irace_2 {c |}  {res} .0598426   .0109968     5.44   0.000
.0382889    .0813963
{txt}    _Irace_3 {c |}  {res}-.0278394   .0586741    -0.47   0.635
-.142841    .0871622
{txt}    _Irace_4 {c |}  {res} .0772966   .0113228     6.83   0.000
.055104    .0994893
{txt}    _Irace_5 {c |}  {res} .0778603   .0144853     5.38   0.000
.0494691    .1062515
{txt}    _Irace_6 {c |}  {res}-.0842987.

However, when I use parmby with the logisitic command:

parmby "xi: logistic outcome wkend i.race i.sex id chf arythm valve pulmcirc
perivasc para neuro chrnlung dm dmcx hypothy renlfail liver ulcer aids lymph
mets tumor arth coag obese wghtloss lytes bldloss anemdef alcohol drug psych
depress htn_c, robust", saving(drg`drg'Mort.dta, replace)idstr(`drg')
}

I don't seem to get accurate extraction of the Odds Ratio coefficients.
Instead, parmby only extracts the specific coefficients specified in the
parmby command- this does not include the Odds Ratio for the logistic
command.  So the file that parmby creates with logisitic is not useful to me
and I'm forced to page through a very very long Log File to see my results.

Is there a way to get the parmby command to extract the Odds Ratio?

Thanks
Pete

*
*   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/
```