SystemObject Extreme.StatisticsLinkFunction
Namespace:
Extreme.Statistics
Assembly:
Extreme.Numerics (in Extreme.Numerics.dll) Version: 8.1.1
public abstract class LinkFunction
Public MustInherit Class LinkFunction
public ref class LinkFunction abstract
[<AbstractClassAttribute>]
type LinkFunction = class end
The LinkFunction type exposes the following members.
| Name | Description |
---|
 | LinkFunction | Initializes a new instance of the LinkFunction class |
Top
| Name | Description |
---|
 | DerivativeAt |
Evaluates the derivative of the link function.
|
 | Equals | Determines whether the specified object is equal to the current object. (Inherited from Object.) |
 | Finalize | Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (Inherited from Object.) |
  | FromName |
Returns the link function by its name.
|
 | GetHashCode | Serves as the default hash function. (Inherited from Object.) |
 | GetType | Gets the Type of the current instance. (Inherited from Object.) |
 | Inverse |
Evaluates the inverse of the link function.
|
 | MapInto |
Evaluates the link function for a set of values.
|
 | MemberwiseClone | Creates a shallow copy of the current Object. (Inherited from Object.) |
  | NegativeBinomial |
Returns the negative binomial link function for the specified parameter value.
|
  | OddsPower |
Returns a link function that uses an odds power ratio.
|
  | Power |
Returns the power link function for the specified exponent.
|
 | SecondDerivativeAt |
Evaluates the second derivative of the link function.
|
 | ToString | Returns a string that represents the current object. (Inherited from Object.) |
 | ValueAt |
Evaluates the link function.
|
Top
Top
Use an instance of the LinkFunction class to define the relationship between the
dependent variable and the linear combination of predictor variables in a
GeneralizedLinearModel. Each ModelFamily has a canonical
link function that is used if no link function is specified.
The instance members of this class are used by the GeneralizedLinearModel
class and are of little interest to end users.
Instead, set the LinkFunction property of the
GeneralizedLinearModel class to the appropriate field or method result.
The following predefined link functions are available:
Member | Description |
---|
Identity | The identity function. This is the canonical link function for the normal family. |
Log | The natural logarithn. This is the canonical link function for the Poisson family. |
Logit | The logit function. This is the canonical link function for the binomial family (logistic regression). |
Probit | The cumulative normal distribution function. This is used with the binomial family in probit regression. |
ComplementaryLogLog | The complementary log-log function. |
Reciprocal | The reciprocal (1 / x) function. This is the canonical link function for the gamma family. |
ReciprocalSquared | The square of the reciprocal function. |
Identity | The identity function. This is the canonical link function for the normal family. |
Identity | The identity function. This is the canonical link function for the normal family. |
Identity | The identity function. This is the canonical link function for the normal family. |
Identity | The identity function. This is the canonical link function for the normal family. |
Identity | The identity function. This is the canonical link function for the normal family. |
Reference