Nick
[email protected]
Steven Gorlé
> From an epistemological point of view, you are mixing up the
> explanandum
> with the explanans, I would try to avoid that.
> You are trying to explain the variation of y/x - which is
> partly dependent
> on x, as the response variable is a ratio of x - with the
> variation of x.
> From a statistical point of view, I would expect an R squared
> inflation and
> maybe some implications on the type of relationship (eg. linearity
> assumption). I would double check the basic regression diagnostics.
> However, I am not sure what the rules of thumb are in this case, I am
> learning but still a novice.
> Is there a possibility to correct for the R square inflation?
> Can it be
> done?
*
* 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/
