PartialSumOfSquares
PartialSumOfSquares
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.
Details and Options
- 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.
Text
Wolfram Research (2007), PartialSumOfSquares, Wolfram Language function, https://reference.wolfram.com/language/RegressionCommon/ref/PartialSumOfSquares.html.
CMS
Wolfram Language. 2007. "PartialSumOfSquares." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/RegressionCommon/ref/PartialSumOfSquares.html.
APA
Wolfram Language. (2007). PartialSumOfSquares. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/RegressionCommon/ref/PartialSumOfSquares.html