AdjustedRSquared

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

AdjustedRSquared
is a possible value for the RegressionReport option to Regress and DesignedRegress which represents the adjusted coefficient of determination.

DetailsDetails

  • To use AdjustedRSquared, 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`"].
  • AdjustedRSquared gives a modified version of the coefficient of determination RSquared which adjusts for the number of parameters in the model.
  • AdjustedRSquared is equal to 1-(n-1)/(n-p)(1-RSquared) where n=Length[data] and p is the number of parameters in the model.

ExamplesExamplesopen allclose all

Basic Examples  (1)Basic Examples  (1)

In[1]:=
Click for copyable input

Sample data:

In[2]:=
Click for copyable input

AdjustedRSquared and RSquared for a linear regression:

In[3]:=
Click for copyable input
Out[3]=