MultipleLinearRegressionRegress Method (Double, Double, Boolean)

Note: This API is now obsolete.

Performs the regression using the input vectors and output data, returning the sum of squared errors of the fit.

Namespace: Accord.Statistics.Models.Regression.Linear
Assembly: Accord.Statistics (in Accord.Statistics.dll) Version: 3.8.0

Syntax

Copy

[ObsoleteAttribute("Please use the OrdinaryLeastSquares class instead.")]
public virtual double Regress(
	double[][] inputs,
	double[] outputs,
	bool robust
)

<ObsoleteAttribute("Please use the OrdinaryLeastSquares class instead.")>
Public Overridable Function Regress ( 
	inputs As Double()(),
	outputs As Double(),
	robust As Boolean
) As Double

Request Example View Source

Parameters

inputs: Type: SystemDouble
The input vectors to be used in the regression.
outputs: Type: SystemDouble
The output values for each input vector.
robust: Type: SystemBoolean
Set to true to force the use of the SingularValueDecomposition. This will avoid any rank exceptions, but might be more computing intensive.

Return Value

Type: Double
The Sum-Of-Squares error of the regression.

Reference

MultipleLinearRegression Class

Regress Overload

Accord.Statistics.Models.Regression.Linear Namespace