What is the partitioning of a regression?

1 Answer
May 30, 2016


Regression partitions are: the sum of squares predicted and the sum of squares error.


Regression can divide the variation in Y (the dependent Variable) into two parts: the variation of the predicted scores and the variation of the errors of prediction. The variation of Y is called the sum of squares Y and is defined as the sum of the squared deviations of Y from the mean of Y. In the population, the formula is

#SSY = Sigma(Y - mu_Y)^2#

where SSY is the sum of squares Y, Y is an individual value of Y, and #μ_Y# is the mean of Y.

Source: http://onlinestatbook.com/2/regression/partitioning.html