Like at least some others I am somewhat bemused
by this thread.
The need to compare models is something we perhaps
can all relate to. My own bias is that I would
rather look at two residual vs fitted plots or
even observed vs fitted plots than play games
with R-square, however customary that may be.
Measuring how well you have done something
is not going to tell much about why you
are doing well or badly, or where to move next.
Nick
[email protected]
[email protected]
> Thank you very much for your attention. I really appreciate
> it. As Stas points
> out, I have two different samples with the same model. My
> first sample
> consists of firms observed for a number of years, the second
> is made of firms
> (some firms are the same as before, some are different)
> observed for a
> subsequent period...thus do you suggest to use an F- test?How
> could I compute
> it in 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/
