Talk:Sum of squares

From Wikipedia, the free encyclopedia

This article should be merged with some others, but least squares is not the right one. Michael Hardy 23:51, 26 July 2006 (UTC)

I agree; Least squares is about so much more.
How about merging Sum of squares into Variance?
Reasons: The Sum of squares article is a lot like Variance, but makes a few good points which Variance could make better:

1. Sum of squares gives a more patient explanation of where the term Deviation comes from.
2. Sum of squares explains in more depth that the reason for dividing the sum of squares by n or n-1 is to keep the variance from growing linearly as more samples are gathered.

JEBrown87544 17:39, 27 July 2006 (UTC)

No, not variance. Least squares is NOT about "so much more". A whole book can be written on "sum of squares", and was--a fairly long one, by Henry Scheffe. If it's to be merged into something, maybe it should be analysis of variance. I'll be back to add some material.... Michael Hardy 21:16, 27 July 2006 (UTC)

You don't believe that Sum of squares overlaps with the Least squares and regression analysis section of Least squares?

In my experience, when people use the term "sums of squares", they use it in reference to ANOVA or fitting a regression model using the Least squares method—instead, they use terms like "random variable", "standard deviation", "variance", or "range" when talking about variation.

Personally, I'd expect an article on sums of squares to discuss the following instead of variance:

• Sums of squares due to regression
• Sums of squares due to error
• Total sum of squares
• Sums of squares due to a given ANOVA factor
• The relationship between the above and ANOVA and regression models

How about this as a counter-proposal?:

• Merge the current content of Sum of squares into Variance
• Rewrite Sum of squares to discuss the role of sums of squares in ANOVA and in the least squares method of fitting regression models

--DanielPenfield 21:34, 27 July 2006 (UTC)

I don't think this should get merged with least squares. The least squares article could reasonably neglect some topics that belong here: how to partition the sum of squares in complicated experimental designs. Michael Hardy 17:49, 3 October 2006 (UTC)