CDM (version 4.6-0)

gdina.wald: Wald Statistic for Item Fit of the DINA and ACDM Rule for GDINA Model

Description

This function tests with a Wald test for the GDINA model whether a DINA or a ACDM condensation rule leads to a sufficient item fit compared to the saturated GDINA rule (de la Torre & Lee, 2013).

Usage

gdina.wald(object)

## S3 method for class 'gdina.wald':
summary(object, \dots)

Arguments

object

A fitted gdina model

...

Further arguments to be passed

Value

• stats
  Data frame with Wald statistic for every item, correponding p values and a RMSEA fit statistic

References

de la Torre, J., & Lee, Y. S. (2013). Evaluating the Wald test for item-level comparison of saturated and reduced models in cognitive diagnosis. Journal of Educational Measurement, 50, 355-373.

Examples

#############################################################################
# EXAMPLE 1: Wald test for DINA simulated data sim.dina
#############################################################################		
data(sim.dina)
data(sim.qmatrix)

# Model 1: estimate GDINA model
mod1 <- gdina( sim.dina , q.matrix = sim.qmatrix ,  rule = "GDINA")
summary(mod1)

# perform Wald test
res1 <- gdina.wald( mod1 )
summary(res1)
# -> results show that all but one item fit according to the DINA rule