ModelFamily Class

Introduction

Mathematics Library User's Guide

Vector and Matrix Library User's Guide

Statistics Library User's Guide

Reference

Represents a family of distributions for the dependent variable in a GeneralizedLinearModel.

Namespace: Extreme.Statistics
Assembly: Extreme.Numerics.Net20 (in Extreme.Numerics.Net20.dll) Version: 3.6.10055.0 (3.6.10077.0)

Syntax

C#
public abstract class ModelFamily

Visual Basic (Declaration)
Public MustInherit Class ModelFamily

Visual C++
public ref class ModelFamily abstract

F#
[<AbstractClassAttribute>] type ModelFamily = class end

Remarks

Use the ModelFamily class to specify the probability distribution of the errors in a generalized linear model regression analysis.

Set the ModelFamily property of the GeneralizedLinearModel to one of the predefined fields or methods:

Member	Description
Normal	The dependent variable has a normal distribution. This is the default.
Binomial	The dependent variable has a binomial distribution. This is used for logistic regression.
Gamma	The dependent variable has a gamma distribution.
InverseGaussian	The dependent variable has an inverse Gaussian distribution.
NegativeBinomial	The dependent variable has a negative binomial distribution. This is a method that requires the total number of cases as a parameter.
Poisson	The dependent variable has a Poisson distribution. This is used for count data in Poisson regression.

Most of the members of this class are used internally. Two members that may be of interest are the IsLinkFunctionCompatible(LinkFunction) method, which checks if a LinkFunction is compatible with the model family, and the CanonicalLinkFunction property, which returns the canonical link function for the model family.

Inheritance Hierarchy

System..::.Object
Extreme.Statistics..::.ModelFamily

Syntax

Remarks

Inheritance Hierarchy

See Also