Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: coding categorical variables


From   "Dimitriy V. Masterov" <dvmaster@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: coding categorical variables
Date   Wed, 5 Dec 2007 04:03:38 -0500

I believe there are three dummy variables: child1, child2 and child3,
where child1 is equal to 1 if child==1 and is 0 if child !=1, and so
on. The notation child* is shorthand for child1 child2 child3. The
nocons option tells Stata not to include a constant, so that this set
of dummies is not collinear.

As far as statistical interpretation, using dummies instead of child
allows the effect of going from 0 to 1 kids to differ from the effect
of going from 1 to 2 (and so on). It's a more flexible specification.

HTH,
DVM

On Dec 5, 2007 3:48 AM, Sharif S. Aly <saly@ucdavis.edu> wrote:
> Hello everyone,
> I was reading the stata 10 "Longitudinal/ panel data" book specifically
> xtmelogit example page 233 and came across a model with "child", a
> categorical variable of 3 levels (if I read this correctly) that was
> coded in the syntax of the fixed effects if the model as "child*" What
> does the star (*) imply?
> Best regards,
> Sharif
>
> *
> *   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/



© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index