Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Oaxaca and categorical variables


From   "Ben Jann" <ben.jann@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Oaxaca and categorical variables
Date   Mon, 24 Nov 2008 21:36:57 +0100

A dummy variable for the reference category must exist in the data. So
if, say, condnum has 9 categories, 1 through 9, you need nine dummies,
one for each category. In the main model, you can only specify eight
dummies (to prevent perfect collinearity), but if you use the
categorical() option then the 9th dummy has to exists and you have to
identify it.

For at each one of the dummy groups in your example oaxaca cannot find
such a reference dummy variable.

ben

On Mon, Nov 24, 2008 at 5:51 PM, Luana Marques Garcia
<luana.garcia@gmail.com> wrote:
> Hi Everyone,
>
> I am trying to use Oaxaca by Ben Jann of May 08 with the categorical
> option and I dont know why I get the error:
>
>      "categorical(): no reference indicator found".
>
> The command I am running is the following:
>
> .oaxaca ln_hwage educa age exper expersq condnum1-condnum8 formal
> urban uf1-uf27 sector1-sector12 if female==0, by(white) noisily
> weight(0) eform svy categorical(uf? uf??, condnum?, sector? sector??).
>
> Does anyone know why?
>
> Thanks a lot,
> Luana
> *
> *   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/
>
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index