# NOT RUN {
#############################################################################
# EXAMPLE 1: Several models for sim.dina data
#############################################################################
data(sim.dina, package="CDM")
data(sim.qmatrix, package="CDM")
dat <- sim.dina
q.matrix <- sim.qmatrix
#--- Model 1: GDINA model
mod1 <- CDM::gdina( data=dat, q.matrix=q.matrix)
summary(mod1)
dmod1 <- CDM::IRT.data(mod1)
str(dmod1)
#--- Model 2: DINA model
mod2 <- CDM::din( data=dat, q.matrix=q.matrix)
summary(mod2)
dmod2 <- CDM::IRT.data(mod2)
#--- Model 3: Rasch model with gdm function
mod3 <- CDM::gdm( data=dat, irtmodel="1PL", theta.k=seq(-4,4,length=11),
centered.latent=TRUE )
summary(mod3)
dmod3 <- CDM::IRT.data(mod3)
#--- Model 4: Latent class model with two classes
dat <- sim.dina
I <- ncol(dat)
# define design matrices
TP <- 2 # two classes
# The idea is that latent classes refer to two different "dimensions".
# Items load on latent class indicators 1 and 2, see below.
Xdes <- array(0, dim=c(I,2,2,2*I) )
items <- colnames(dat)
dimnames(Xdes)[[4]] <- c(paste0( colnames(dat), "Class", 1),
paste0( colnames(dat), "Class", 2) )
# items, categories, classes, parameters
# probabilities for correct solution
for (ii in 1:I){
Xdes[ ii, 2, 1, ii ] <- 1 # probabilities class 1
Xdes[ ii, 2, 2, ii+I ] <- 1 # probabilities class 2
}
# estimate model
mod4 <- CDM::slca( dat, Xdes=Xdes)
summary(mod4)
dmod4 <- CDM::IRT.data(mod4)
# }
Run the code above in your browser using DataLab