Class KrigingInterpolation1D
java.lang.Object
smile.interpolation.KrigingInterpolation1D
- All Implemented Interfaces:
Serializable, Interpolation
Kriging interpolation for the data points irregularly distributed in space.
Kriging belongs to the family of linear least squares estimation algorithms,
also known as Gauss-Markov estimation or Gaussian process regression.
This class implements ordinary kriging for interpolation with power variogram.
- See Also:
-
Constructor Summary
ConstructorsConstructorDescriptionKrigingInterpolation1D(double[] x, double[] y) Constructor.KrigingInterpolation1D(double[] x, double[] y, double beta) Constructor. -
Method Summary
Modifier and TypeMethodDescriptiondoubleinterpolate(double x) Given a value x, return an interpolated value.toString()
-
Constructor Details
-
KrigingInterpolation1D
public KrigingInterpolation1D(double[] x, double[] y) Constructor. The power variogram is employed for interpolation.- Parameters:
x- the tabulated points.y- the function values atx.
-
KrigingInterpolation1D
public KrigingInterpolation1D(double[] x, double[] y, double beta) Constructor. The power variogram is employed for interpolation.- Parameters:
x- the tabulated points.y- the function values atx.beta- the parameter of power variogram. The value of β should be in the range1 <=β< 2. A good general choice is 1.5, but for functions with a strong linear trend, we may experiment with values as large as 1.99.
-
-
Method Details
-
interpolate
public double interpolate(double x) Description copied from interface:InterpolationGiven a value x, return an interpolated value.- Specified by:
interpolatein interfaceInterpolation- Parameters:
x- a real number.- Returns:
- the interpolated function value.
-
toString
-