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: FW: Model SS/R-square in nl


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: FW: Model SS/R-square in nl
Date   Fri, 1 Jul 2011 08:26:05 +0100

You are quite correct on this point. Sorry; I was thinking of power
functions x^constant which are a current preoccupation of mine, but
constant^x is indeed 1 when x is 0.

The wider point is that R-square has different definitions which
aren't guaranteed to coincide. If you want R-square to equal the
square of corr(observed, predicted) you need to calculate that
directly. See e.g.

FAQ     . . . . . . . . . . . . . . . . . . . . . . . Do-it-yourself R-squared
        . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  N. J. Cox
        9/03    How can I get an R-squared value when a Stata command
                does not supply one?
                http://www.stata.com/support/faqs/stat/rsquared.html

Although the question there is not yours, the answer is I think relevant.

On Thu, Jun 30, 2011 at 9:24 PM, CJ Lan <CJ@jupiter.fl.us> wrote:
[...]

> The curve will not be forced through the origin.  The curve of the 1st model starts at (b0+b1=45.6) and decreases at an exponential rate.  Similarly the curve of the 2nd model starts at (b1=44.5) and decreases at a similar exponential rate.

*
*   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