GeneralLinear.RSquaredAdjusted Method 

Evaluates the Adjusted R² (aka Adjusted Multiple Coefficient of Determination) of the (multi-linear) regression considered.

Return Value

The Adjusted R² of the multi-linear regression equation.

Remarks

Further Details

Here we evaluate the Adjusted R² which safe guards against the over-estimation of the effect of adding additional variables to a linear regression model. For example, deciding if or if not an additional variable is statistically significant for a model the (traditional) R² measure (see RSquared) can lead to misleading results since in all cases the measure will increase. Therefore, in order to guard against over-estimating the effect of adding additional variables to a model the Adjusted R² was introduced.

When R² is small and the number of Variables is large

In the case when R² is small and the number of variables is large then the Adjusted R² can be negative. In such instances the adjustment itself is adjusted and set to 0.

Preconditions

Please note that before this method is called you must have already performed the following tasks:

1. Set the Fitting Function using SetFunctionBasis
2. Fit the function using SetGeneralFit

See Also

GeneralLinear Class | WebCab.COM.Statistics.CurveFitting Namespace | RSquared - Evaluates the R2 statistic (without adjustment for the number of independent variables used by the regression model).