Re: Antwort: st: why is a category being dropped by Stata?

[Suzy <scott_788@wowway.com>]

When I include the nocons syntax, I get the same problem, but now with 
the c_n_demo_1 dummy is dropped. BTW, I've run quite a few regressions 
using the xi: comman with other datasets and this has never happened 
before.  (I tried a regression without including on 1-1145 observations 
and Stata drops c_n_demo_2, like without the nocons syntax when I kept 
in the 1/1145.


xi: regress ln_pbb demo_yn  i.c_n_demo newrace2 bldyr_pp i.age_cat  
sex2  in 1/1145, nocons

------------------------------------------------------------------------------

     ln_pbb |      Coef.   Std. Err.      t    P>|t|     [95% Conf. 
Interval]

-------------+----------------------------------------------------------------

    demo_yn |   .0744378   .0483279     1.54   0.124     -.020384    
.1692596

_Ic_n_demo_1 |  (dropped)

_Ic_n_demo_2 |   .2674317   .1162665     2.30   0.022     .0393109    
.4955525

   newrace2 |    .541398   .0552086     9.81   0.000      .433076      
.64972

   bldyr_pp |   .6846982   .0580307    11.80   0.000     .5708389    
.7985574

_Iage_cat_1 |   .6328892   .0603672    10.48   0.000     .5144456    
.7513327

_Iage_cat_2 |   .4941141   .0600306     8.23   0.000     .3763311    
.6118971

       sex2 |   .1092572   .0396376     2.76   0.006     .0314863    
.1870282

------------------------------------------------------------------------------

Hans J. Baumgartner wrote:


> Hi Suzy,
>
> the xi indcatvargenerates dummies for each category. Since you did not use 
> the nocons option, one dummy has to be dropped. Otherwise the dummies were 
> perfectly collinear with the constant, since they add up to unity. So 
> everything is correct and the coefficient on _I_indcatvar should be 
> interpreted relative to the dummy-base. 
> Hans
>
> owner-statalist@hsphsun2.harvard.edu schrieb am 11/07/2005 14:30:20:
>
>  
>
> > Dear Statamembers,
> >
> > I have a categorical variable, coded as 0, 1, 2.
> >
> > When I do a a simple regression equation using "xi: regress depvar, 
> > indcontvar, i.indcatvar, "
> >
> > Stata drops the category 2  (n=40/1196)
> >
> > I have other categorical variables  in the model, but everything else 
> > looks OK.
> >
> > I have no idea why it's being dropped.
> >
> > thanks for any insight.
> > Suzy
> > *
> > *   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/
>
>
>
>  
*
*   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/