bmpt-class: Class '"bmpt"'

In MPTinR2: Analyze Multinomial Processing Tree Models

Description

Objects holding the results of fitting multinomial procesing tree (MPT) models. bmpt objects are fits to models which are member of L-BMPT (bmpt.model-class; see also Purdy & Batchelder, 2009), mpt objects to those binary MPTs that are not represented in a way that is compatible to L-BMPT.

Objects from the Class

Objects can be created by a call to fit.mpt. They hold all information: the model as a model object, the data, and the results from the fitting (e.g., parameters, likelihood values,...).

Slots

model:

The model object, see bmpt.model-class

observed.data:

Array. The data entered.

predicted.data:

Aray. The predicted data.

C.matrix:

A list holding the "C" matrices which contain the relative frequency of data per branch and tree.

g2:

Numeric. The G^2 value of the fitted model.

logLikelihood:

Numeric. The (-2*) Log-Likelihood of the fitted model.

estimates:

Matrix. The parameter estimates of the fitted model.

multifit:

Logical. Does the data contain more than one individual dataset?

hessian:

List of Hessian matrices

default.ci:

Numeric. Standard size of confidence intervals.

typeHessian:

List containing the type(s) of Hessian matrix. Can be either, "expected" or "observed". Only in class bmpt.

hfail:

Numeric. Did calculation of expected hessian fail (=1)? Only in class bmpt.

fia:

List of Fisher Information Approximation results. Currently not implemented. Only in class bmpt.

parametric.ci:

List containing the parametric bootstrapped confidence intervall. Not yet implemented. Only in class bmpt.

nonparametric.ci:

List containing the parametric bootstrapped confidence intervall. Not yet implemented. Only in class bmpt.

Extends

bmpt extends mpt.

Methods

show

signature(object = "mpt"): Method for displaying overall results.

parameters

see parameters-methods

goodness.of.fit

signature(object = "mpt"): Function to compute and display the (-2 *) Log-Likelihood, the G^2, the degrees of freedom and the p for the model fit.

information.criteria

signature(object = "mpt"): Function to compute and display AIC, BIC, and (when computed) FIA.

default.ci

signature(object = "mpt"): Accessor function for the default.ci slot. A replacement function exists as well!

observed.data

signature(object = "mpt"): Accessor function for the observed data.

predicted.data

signature(object = "mpt"): Accessor function for the predicted data.

logLikelihood

signature(object = "mpt"): Accessor function for the (-2 *) Log-Likelihood of the fitted model.

estimates

signature(object = "mpt"): Accesor function for the parameter estimates. This function returns the values of the fitted parameters (i.e., when inequality restrictions are present the parameters of the reparametrized model are presented)

check

signature(object = "mpt"): Very informative function that returns a list with useful information of the fitted model:
Do probabilities sum to 1?; number of trees; number of categories; number of free parameters in the final model; names of free parameters in the final model; number of fixed parameters in the final model; names of fixed parameters in the final model; names of parameters in the initial model (i.e., no restrictions applied); maximum number of branches per category; vector with number of branches per category; degrees of freedom; is model a member of L-BMPT?

Author(s)

Henrik Singmann

See Also

fit.mpt

Examples

showClass("bmpt")

MPTinR2 documentation built on May 2, 2019, 4:44 p.m.