plfm (version 2.2.6)

summary.bayesplfm: Summarizing Bayesian probabilistic latent feature analysis

Description

The function summary.bayesplfm summarizes the output of the object generated by the bayesplfm function.

Usage

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

Value

call

Parameters used to call the function.

descriptivefit

A list with two measures of descriptive fit on the J X K table: (1) the correlation between observed and expected frequencies, and (2) the proportion of the variance in the observed frequencies accounted for by the model.

objpar

A J X F matrix with the posterior mean of the object parameters computed on all iterations and chains in the sample.

attpar

A K X F matrix with the posterior mean of the attribute parameters computed on all iterations and chains in the sample.

p95objpar

95 percent posterior intervals of object parameters.

p95attpar

95 percent posterior intervals of attribute parameters.

Rhatobjpar

Rhat convergence values for object parameters.

Rhatattpar

Rhat convergence values for attribute parameters.

Arguments

object

Bayesian probabilistic latent feature analysis object returned by bayesplfm

...

Further arguments are ignored

Details

The summary of the Bayesian probabilistic latent feature analysis objects displays:

1. The parameters used to call the bayesplfm function.

2. 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).

3. The posterior mean of the object- and attribute parameters.

4. 95 percent posterior intervals for the object- and attribute parameters.

5. Rhat convergence values for object- and attribute parameters (if Nchains>1).

See Also

bayesplfm

Examples

if (FALSE) {

##load car data
data(car)

## compute 5 runs of disjunctive model with 2 features
carem2<-plfm(maprule="disj",freq1=car$freq1,freqtot=car$freqtot,F=2,M=5)

## Compute a sample of the posterior distribution 
## for the disjunctive model with two features
## use the posterior mode obtained with the previous plfm analysis
carbayes2<-bayesplfm(maprule="disj",freq1=car$freq1,freqtot=car$freqtot,F=2,
                      maxNiter=500,Nburnin=0,Nstep=100,Nchains=2,
                      start.bayes="fitted.plfm",fitted.plfm=carem2)


## compute a summary of the object generated by bayesplfm
summarycarbayes2<-summary(carbayes2)
}