Talk:Residual sum of squares


 * The following discussion is an archived discussion of the . Please do not modify it. Subsequent comments should be made in a new section on the talk page. No further edits should be made to this section. 

no consensus--Jorfer 16:03, 3 July 2007 (UTC)

Merge
I've left a message on the project talk page to see if someone can help look into a possible merge. Kevin 08:39, 29 June 2007 (UTC)


 * Maybe instead of merging this into least squares, it should be merged into a new article called partition of the sum of squares, a topic on which a thick volume could be written. Michael Hardy 23:20, 29 June 2007 (UTC)

I don't think least squares is really the right merge target. Least squares is more about regression (that is, fitting a function to a set of (x,y) pairs), while this is about simple averaging (or central tendency if you like: fitting a single point to a set of x values). I suggest a different merge target: arithmetic mean, specifically a slight expansion of the "Formulation as an optimization problem" section. Probably total sum of squares could also be included in the merge. —David Eppstein 19:05, 1 July 2007 (UTC)


 * The above discussion is preserved as an archive of the . Please do not modify it. Subsequent comments should be made in a new section on this talk page. No further edits should be made to this section.

Excel formula: SUMXMY2
Do people think it would be instructive to mention that this can be calculated in Excel using the function SUMXMY2(actual_values, predicted_values) ? Ts4079 (talk) 12:51, 15 August 2011 (UTC)