Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: R-squared measures proposed by Cameron and Windmeijer (1996) in stata


From   Ronan Conroy <[email protected]>
To   "[email protected]" <[email protected]>
Subject   Re: st: R-squared measures proposed by Cameron and Windmeijer (1996) in stata
Date   Fri, 25 Mar 2011 10:22:03 +0000

On 25 Mar 2011, at 09:21, Nick Cox wrote:

> You need to think about what it would mean in your field to have
> perfect predictions. It means that the data provide a complete
> description _and_ the model captures the generating process exactly.
> Or it would mean that you were using a model with too many parameters.
> In most observational fields even large datasets provide only partial
> data and the model is at best a caricature of the underlying process.

I would second Nick's observations, and add a reminder that you cannot explain 100% of variance if your measurement instruments contain error, which is, of course, what happens in real life and sociology.

The whole notion of R^2 is somehow comforting for those who don't want to have to think too carefully about models. People often say "these factors explained X% of variance". Of course, the statistical model isn't an explanation. Explanations link phenomena by (unobservable) causal links. Statistical models look for shared variation between measurements. Different idea. 



Ronán Conroy
[email protected]
Associate Professor
Division of Population Health Sciences
Royal College of Surgeons in Ireland
Beaux Lane House
Dublin 2


*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index