Home > Extreme Optimization Mathematics Library for .NET > Reference > Extreme.Mathematics.Curves Namespace
Represents a Curve that can be used for a non-linear regression calculation.
For a list of all members of this type, see NonlinearCurve Members.
System.Object
Curve
NonlinearCurve
Use the NonlinearCurve class to represent a curve suitable for use in a non-linear curve fitting. The NonlinearCurveFitter class works only with curves that derive from NonlinearCurve. See this class for details on how to perform a least squares fit.
NonlinearCurve is an abstract class and cannot be instantiated directly. Instead, derive your own class from NonlinearCurve, or use one of the predefined classes listed in the following table:
| Class | Description |
|---|---|
| ExponentialCurve | A sum of exponential terms. |
| FourParameterLogisticCurve | A standard 4-parameter logistic curve. |
| FiveParameterLogisticCurve | A 5-parameter logistic curve that includes an asymmetry factor. |
| GaussianCurve | A 4-parameter Gaussian 'bell' curve. |
| LorentzCurve | A 4-parameter Lorentz peak curve. |
| RationalCurve | A quotient of two polynomials. |
| SineCurve | A 4-parameter periodic curve. |
Note to inheritors: You must override the ValueAt method. If possible, you should also override the FillPartialDerivatives and SlopeAt methods. By default, a numerical approximation is used as the derivative.
Namespace: Extreme.Mathematics.Curves
Assembly: Extreme.Mathematics (in Extreme.Mathematics.dll)
NonlinearCurve Members | Extreme.Mathematics.Curves Namespace