Statalist


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

st: Adjusted generalized r-squared, anyone?


From   "Clive Nicholas" <[email protected]>
To   [email protected]
Subject   st: Adjusted generalized r-squared, anyone?
Date   Thu, 8 Jan 2009 09:52:39 +0000

Is it legitimate to substitute Nagelkerke (1991) r-squared, thus

\bar{R}^{2}_{G}=1-\left( \frac{L(0)}{L(\hat{\theta})} \right)^{2/n}

in the equation for adjusted ('normal') r-squared, thus

\bar{R}^{2} = 1-(1-R^{2})\frac{n-1}{n-k-1}

?

I'd like to say the answer to this is obvious, but it isn't to me.
Google searching turned up nothing, and although there is a correction
for Ns in Nagelkerke r-squared, it doesn't appear to be the full df
correction that we see in adjusted r-squared.

Moreover, my lack of statistical sophistication daren't suggest

\bar{R}^{2}_{G}=1-\left( \frac{L(0)}{L(\hat{\theta})} \right)^{2/{n-1}{n-k-1}}

Or could it? Has it been already? Thoughts?

-- 
Clive Nicholas

[Please DO NOT mail me personally here, but at
<[email protected]>. Please respond to contributions I make in
a list thread here. Thanks!]

"My colleagues in the social sciences talk a great deal about
methodology. I prefer to call it style." -- Freeman J. Dyson.
*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index