[Top][All Lists]

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

Re: leasqr question

From: Dirk Eddelbuettel
Subject: Re: leasqr question
Date: Fri, 06 Sep 2002 08:12:58 -0500

> I don't agree.  No matter how the regression is accomplished (linear,
> nonlinear, least squares, random guesses, goat entrails), the geometry
> should work just fine.  You have a set of observed values and a

Yes, you can always /compute/ the same statistic, it merely doesn't
have the same statistical properties -- the "restricted" model (of
variation around the mean) is no longer nested within the "unrestricted"
model (the a nonlinear model just fitted), so that the resulting R2 
could for example be negative.  It just doesn't apply in the same
/statistical/ sense, which is why few (if any ?) packages compute it,
even though as you point out, it can easily be done.


According to the latest figures, 43% of all signatures are totally

Octave is freely available under the terms of the GNU GPL.

Octave's home on the web:
How to fund new projects:
Subscription information:

reply via email to

[Prev in Thread] Current Thread [Next in Thread]