April 2009

edit

  Welcome to Wikipedia. Although everyone is welcome to contribute constructively to the encyclopedia, adding content without citing a reliable source, as you did to Polynomial regression, is not consistent with our policy of verifiability. Take a look at the welcome page to learn more about contributing to this encyclopedia. If you are familiar with Wikipedia:Citing sources, please take this opportunity to add references to the article. Thank you. --AbsolutDan (talk) 02:41, 3 April 2009 (UTC)Reply

Polynomial regression

edit

Polynomial regression is badly written and will need a lot of work to be worthwhile.

I have replaced some of your material with this:

A commonplace facile misconception is that linear regression is so called because one fits a straight line. That is an error. In fact polynomial regression as characterized here is an instance of linear regression, although the curves one is fitting are not straight lines.

Your statement that linear regression is a special case, rather than the other way around, clearly demonstrates that you know very little about this. I urged you to read linear regression. That is a flawed article, but you'll learn a lot from it. You clearly do not know that material.

I'm not altogether convinced that polynomial regression is worth a separate article, unless perhaps one recognizes it as a special case of linear regression and emphasizes things that don't apply in linear regression in general.

Let's be clear: EVERY CASE OF POLYNOMIAL REGRESSION AS YOU HAVE DEFINED IT IS A CASE OF LINEAR REGRESSION; the fact that one is not fitting a line does not make it non-linear in the relevant sense. Michael Hardy (talk) 05:12, 7 April 2009 (UTC)Reply