fmmr6: The Abstract Class of Finite Mixture Models on R6 (fmmr6)

In wudongjie/fmmr6: The R Implementation of Finite Mixture Modellings on the R6 Class System

The Abstract Class of Finite Mixture Models on R6 (fmmr6)

Description

An abstract R6Class for the Finite Mixture Models.

Value

No return

The R6 Structure of the fmmr6 Package

The fmmr6 package adopts an Object-Oriented (OO) design with the help of R6. It contains three main blocks of constructing and fitting a finite mixture model (FMM):

• Finite Mixture Modelling: Finite Mixture Modelling can the way we construct our finite mixture models. These modelling techniques are organized under fmmr6 class. In the current version, we have only developed the mixture of generalized linear models, which is the fmglm class. We are going to add more modelling techniques such as the mixture of generalized linear models using a panel data structure xtfmglm.

• Methods to fit a FMM models: The fitting methods such as EM-algorithm (em) and Maximum Likelihood Estimation (mle) are organized under the AbstractMethod class. In this way, it is convenient to pickup a different method to fit the FMM models.

• Families of distributions: Different families of distributions are organized under the Family class. Currently, the package only supports Gaussian distributions (FamilyNormal), Poisson distributions (FamilyPoisson), Logit Models with Gaussian distributions (FamilyLogit), and Multinomial Logit Models with Gaussian distributions (FamilyMultiNomial). These distributions will be sent to a Mixer class to generate a mixture of distributions based on the setting of the finite mixture model.

Methods

Public methods

• fmmr6$new()

• fmmr6$fit()

• fmmr6$summarize()

• fmmr6$predict()

• fmmr6$clone()

---

Method new()

Create a new instance of this R6 R6::R6Class class.

Usage

fmmr6$new()

---

Method fit()

Fit the fmmr6 model

Usage

fmmr6$fit()

---

Method summarize()

Generate a summary for the result.

Usage

fmmr6$summarize()

---

Method predict()

Predict the outcome given the fitted model.

Usage

fmmr6$predict()

---

Method clone()

The objects of this class are cloneable with this method.

Usage

fmmr6$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Author(s)

Dongjie Wu

wudongjie/fmmr6 documentation built on June 24, 2022, 2:48 p.m.