On Tue, Mar 5, 2013 at 11:11 PM, <owner-statalist@hsphsun2.harvard.edu> wrote:
> FP is measured as the ratio of foreign employment to total employment
> in a given industry. I generate the variable FP using the following
> commands:
>
> -bys ind year: egen F_EMP = total(employment) if Foreign ==1
>
> gen FP= F_EMP/IND_EMP
>
>
> The FP variable is only generated for foreign firms. How then can this
> be manipulated so I can regress foreign participation against
> employment growth of domestic firms only (Foreign=0)?
If the values tend to be between say .3 and .7 and are based on
essentially the same N within each industry then an ordinary linear
panel model is likely to work fine. If not, you need to deal with the
skew and would likely benefit from using a model such as -xtmelogit-
with the count/total formulation for grouped binomial data. There are
other possibilities, such as using -gee-.
--
JVVerkuilen, PhD
jvverkuilen@gmail.com
"It is like a finger pointing away to the moon. Do not concentrate on
the finger or you will miss all that heavenly glory." --Bruce Lee,
Enter the Dragon (1973)
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
