Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: regression without constant


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: regression without constant
Date   Fri, 5 Nov 2004 10:26:18 -0000

Yes, this is correct. 

I guess this was a step too far for the implementers. 

In the case of -regress- there's an easy solution
either way and in one sense that difference is very minor. 

In the case of -qreg- at least, the extra constraint implied 
by forcing a hyperplane through the origin would seem 
by comparison a much bigger deal. That's just gut instinct
speaking, not a rigorous argument based on algebra or algorithmics. 

Nick 
n.j.cox@durham.ac.uk 

Ypma, Jelmer Yeb
 
> is it correct that -rreg- and -qreg- can't be used in 
> combination with -noconstant-?
> If so, why is this the case? Is there some special reason?

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index