 | MultipleRegressionSvdT Method (Matrix`1T, Matrix`1T) |
Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
Uses a singular value decomposition and is therefore more numerically stable (especially if ill-conditioned) than the normal equations or QR but also slower.
Namespace: MathNet.Numerics.LinearRegression
Assembly: MathNet.Numerics (in MathNet.Numerics.dll) Version: 3.7
SyntaxC#
public static Matrix<T> Svd<T>( Matrix<T> x, Matrix<T> y ) where T : struct, new(), IEquatable<T>, IFormattable
Parameters
- x
- Type: MatrixT
Predictor matrix X - y
- Type: MatrixT
Response matrix Y
Type Parameters
- T
Return Value
Type: MatrixTBest fitting vector for model parameters β
See Also