As of Version 7.0, PartialSumOfSquares has become a property of LinearModelFit.


is a possible value for the RegressionReport option to Regress and DesignedRegress which represents the change in the model sum of squares as nonconstant basis functions are removed.


  • To use PartialSumOfSquares, you first need to load the Regression Common Functions Package. You can do this by using Needs["LinearRegression`"], which will automatically load the Regression Common Functions Package, or you can load the package directly by using Needs["RegressionCommon`"].
  • PartialSumOfSquares is useful for trimming a large set of predictors.
  • Basis functions yielding a small value for the partial sum of squares have less influence on the fit.

See Also

ANOVATable  SequentialSumOfSquares