CDM (version 2.7-7)

data.sda6: Dataset SDA6 (Jurich & Bradshaw, 2014)

Description

This is a simulated dataset of the SDA6 study according to informations given in Jurich and Bradshaw (2014).

Usage

data(data.sda6)

format

The datasets contains 17 items observed at 1710 students. The format is: List of 2 $ data : num [1:1710, 1:17] 0 1 0 1 0 0 0 0 1 0 ... ..- attr(*, "dimnames")=List of 2 .. ..$ : NULL .. ..$ : chr [1:17] "MCM01" "MCM03" "MCM13" "MCM17" ... $ q.matrix:'data.frame': ..$ CM: int [1:17] 1 1 1 1 0 0 0 0 0 0 ... ..$ II: int [1:17] 0 0 0 0 1 1 1 1 0 0 ... ..$ PP: int [1:17] 0 0 0 0 0 0 0 0 1 1 ... ..$ DG: int [1:17] 0 0 0 0 0 0 0 0 0 0 ... The meaning of the skills is CM -- Critique Methods II -- Identify Improvements PP -- Protect Participants DG -- Discern Generalizability

source

Simulated data

References

Jurich, D. P., & Bradshaw, L. P. (2014). An illustration of diagnostic classification modeling in student learning outcomes assessment. International Journal of Testing, 14, 49-72.

Examples

data(data.sda6)
data <- data.sda6$data
q.matrix <- data.sda6$q.matrix

#*** Model 1a: LCDM with gdina
mod1a <- gdina( data , q.matrix , rule="ACDM" , linkfct="logit" ,
                  reduced.skillspace=FALSE )  
summary(mod1a)

#*** Model 1b: estimate LCDM with gdm
mod1b <- gdm( data , q.matrix=q.matrix , theta.k=c(0,1) )  
summary(mod1b)

#*** Model 2: LCDM with hierarchy II > CM
B <- "II > CM"
ss2 <- skillspace.hierarchy(B=B , skill.names= colnames(q.matrix ) )
mod2 <- gdina( data , q.matrix , rule="ACDM" , linkfct="logit" ,
            skillclasses = ss2$skillspace.reduced ,
            reduced.skillspace=FALSE )                        
summary(mod2)

#*** Model 3: LCDM with hierarchy II > CM and DG > CM
B <- "II > CM
      DG > CM"
ss2 <- skillspace.hierarchy(B=B , skill.names= colnames(q.matrix ) )
mod3 <- gdina( data , q.matrix , rule="ACDM" , linkfct="logit" ,
            skillclasses = ss2$skillspace.reduced ,
            reduced.skillspace=FALSE )                        
summary(mod3)

# model comparisons
anova(mod1a,mod2)
anova(mod1a,mod3)
# model fit
summary( modelfit.cor.din(mod1a))
summary( modelfit.cor.din(mod2) )
summary( modelfit.cor.din(mod3) )