plfm (version 2.2.6)

summary.plfm: Summarizing probabilistic latent feature analysis

Description

The function summary.plfm summarizes the main output of plfm including estimates and standard errors for object- and attribute parameters, model selection criteria, and goodness-of-fit measures.

Usage

# S3 method for plfm
summary(object, ...)

Value

call

Parameters used to call the function.

informationcriteria

List of information criteria that can be used for model selection.

chisquaretest

Pearson Chi-square test to evaluate the statistical goodness-of-fit of the model on the J X K object by attribute table of association frequencies.

descriptivefit

A list of measures to evaluate the descriptive goodness-of-fit of the model on the J X K object by attribute table of association frequencies.

objpar

A J X F matrix of estimated object parameters.

SE.objpar

A J X F matrix of estimated standard errors of object parameters.

attpar

A K X F matrix of estimated attribute parameters.

SE.attpar

A K X F matrix of estimated standard errors of attribute parameters

Arguments

object

Probabilistic latent feature analysis object returned by plfm

...

Further arguments are ignored

Author

Michel Meulders

Details

The summary of probabilistic latent feature analysis objects displays:

1. The parameters used to call the plfm function.

2. The value of the loglikelihood, the deviance, the logarithm of the posterior density, the information criteria AIC and BIC.

3. The result of a Pearson chi-square goodness-of-fit test on the J X K table.

4. Information on the descriptive fit of the model (i.e. correlation between observed and expected frequencies. and proportion of the variance in the observed frequencies accounted for by the model).

5. The estimated object- and attribute parameters.

6. Asymptotic standard errors of the object- and attribute parameters.

See Also

plfm, print.plfm, print.summary.plfm

Examples

## Perceptual analysis of associations between car models and car attributes

##load car data
data(car)

##compute the disjunctive model with 4 features
carf4<-plfm(maprule="disj",freq1=car$freq1,freqtot=car$freqtot,F=4,M=1)

## display a summary of the results
summary(carf4)