GaussianMixtureResponse-class: Class "GaussianMixtureResponse"

In mcplR: Multiple Cue Probability Learning in R

Description

Model responses according to a Gaussian mixture.

Objects from the Class

Objects can be created by calls of the form new("GaussianMixtureResponse", ...).

Slots

weights:

A "list", with for each repetition in nTimes, a T*K matrix of mixture weights (T=total number of trials, k = number of mixture components).

means:

A "list", with for each repetition in nTimes, a matrix of mixture means. When component means vary over trials, this should be a T*K matrix (T=total number of trials, k = number of mixture components), else a 1*k matrix.

sds:

A "list", with for each repetition in nTimes, the standard deviation of the mixture components. Currently, only components with identical means are supported, and the values in this slot are set by a single "sd" parameter (see "parameters" slot).

x:

A "matrix", containing values of the response options.

y:

Object of class "matrix", containing dummy coded response variable.

parStruct:

Object of class "ParStruct", specifying parameters and (optional) constraints.

nTimes:

Object of class "NTimes".

Extends

Class "ResponseModel", directly. Class "McplBaseModel", by class "ResponseModel", distance 2.

Methods

fit

signature(object = "GaussianMixtureResponse"): ...

logLik

signature(object = "GaussianMixtureResponse"): ...

predict

signature(object = "GaussianMixtureResponse"): ...

Author(s)

Maarten Speekenbrink

mcplR documentation built on May 2, 2019, 4:42 p.m.