st: Question about the use of ratio variables

[hsini <hsini92@gmail.com>]

Dear all,

I have a question about the use of ratio variables.
Is it problematic to have a regression equation like : (Yi/population) = 
b0+ b1*(Xi/Yi) +b2X2 + error?

Let's say Yi is the number of innovation per region, and Xi is the 
number of small firm innovation.  The ratio variable is a very important 
measure since in my theory it represents the organizational ecology of 
the region.  I excluded regions with zero innovation.  However, I am 
afraid of any function problem since I have Yi on the both side of the 
equation. I have read Bradshaw and Radbill (1987) paper discussing the 
use of ratio variables.  It seems to me they were dealing with the ratio 
is generated by a third variable (Z), which is a bit different from my 
situation.  Any suggestion?


Sincerely,
Hsini Huang
*
*   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/