Re: Formula for Coefficient of Determination (Quadratic Regression)

From: Giobibo (giobibo_at_yahoo.com)
Date: 08/26/04 

Date: Thu, 26 Aug 2004 07:26:27 +0200

On Wed, 25 Aug 2004 15:35:18 -0400, Richard Ulrich
<Rich.Ulrich@comcast.net> wrote:

>Do you mean Y= a*X +b*X^2 + c ?
>
>Most statisticians consider that a linear regression because
>it is linear in the coefficients. Its R^2 is the CD.
>
>Many engineers (inter alia) don't call it linear, but it
>is still the simple case. Here is a post from last year,
>and my response -
>
>Is this a question about computing "R-squared", or
>about using the term "coefficient of determination"?

Dear Richard, thank you for your answer.

Yes, I mean Y= a*X +b*X^2 + c and want to compute R-squared.

II could not find any formula over the net.
This links helped me a little bit, but I have still a lot of dubts:
http://stat.tamu.edu/stat30x/notes/node47.html
http://www.medcalc.be/manual/mpage06-04c.php
http://www.cmh.edu/stats/ask/rsquared.asp

It should be R-squared = 1 - SSRes/SSTotal

where SSRes = Sum (Yesti - Ymean)^2
and SSTotal =Sum (Yi - Ymean)^2

Ymean is the mean of the samples, Yi is the i-sample, Yesti is the
predict i-sample.

Is this right?

Thank you for replying.
Gio

Relevant Pages

  • Re: advise on math course
    ... > Linear and Nonlinear Equations, Linear Least Squares, Eigenvalue ... mainly if you are going to work with engineers. ... > chain models, Markov decision processes, discrete-event simulation ... program to solve his optimization problem. ...
    (comp.theory)
  • Re: linear algebra question
    ... course was multiple integration with volumes, surface integrals, etc. ... For linear algebra, what is the main part of the course? ... For engineers, the use of invertible matrices to solve ... If an engineer wants to solve a system of linear equations she will not be ...
    (sci.math)
  • Re: SW World opinions
    ... good luck in your mission ... I find engineers typically have real trouble with id people because they are ... quite uncomfortable in themselves about things outside the linear, ...
    (comp.cad.solidworks)