CDM (version 4.8-0)

entropy.lca: Test-specific and Item-specific Entropy for Latent Class Models

Description

Computes test-specific and item-specific entropies as test-diagnostic criteria of cognitive diagnostic models (Asparouhov & Muthen, 2014).

Usage

entropy.lca(object)

## S3 method for class 'entropy.lca':
summary(object, digits = 2 ,  \dots)

Arguments

object

Object of class din, gdina or mcdina. For the summary method, it is the result of entropy.lca<

digits

Number of digits to round

...

Further arguments to be passed

Value

• A list with the data frame entropy as an entry.

References

Asparouhov, T. & Muthen, B. (2014). Variable-specific entropy contribution. Technical Appendix. http://www.statmodel.com/7_3_papers.shtml

See Also

See cdi.kli for test diagnostic indices based on the Kullback-Leibler information and cdm.est.class.accuracy for calculating the classification accuracy.

Examples

#############################################################################
# EXAMPLE 1: Entropy for DINA model 
#############################################################################	

data(sim.dina)
data(sim.qmatrix)

# fit DINA Model
mod1 <- din( sim.dina , q.matr = sim.qmatrix, rule = "DINA")
summary(mod1)
# compute entropy for test and items
emod1 <- entropy.lca( mod1 )
summary(emod1)	

#############################################################################
# EXAMPLE 2: Entropy for polytomous GDINA model
#############################################################################

data(data.pgdina)
dat <- data.pgdina$dat
q.matrix <- data.pgdina$q.matrix

# pGDINA model with "DINA rule"
mod1 <- gdina( dat , q.matrix=q.matrix , rule="DINA")
summary(mod1)

# compute entropy
emod1 <- entropy.lca( mod1 )
summary( emod1 )

#############################################################################
# EXAMPLE 3: Entropy for MCDINA model
#############################################################################

data(data.cdm02)
dat <- data.cdm02$data
q.matrix <- data.cdm02$q.matrix

# estimate model with polytomous atribute
mod1 <- mcdina( dat , q.matrix=q.matrix )
summary(mod1)
# computre entropy
emod1 <- entropy.lca( mod1 )
summary( emod1 )