I would be thankful if someone could give me a short breakdown on how to test unidimensionality of polytomous data (likert-scale) using IRT-models in R.
As it is my understanding that the ltm-package is obsolete, I'm looking for an equivalent to ltm::unidimTest() (perhaps within the mirt-package?).
Thank you
Hi Björn Hommel ;
you can use sirt package for this purpose. DETECT and Noharm tests can be conducted with sirt package. You can use expl.detect() function for DETECT method and noharm.sirt() function for NOHARM method.
Hope helps.
AFK
http://statmath.wu.ac.at/research/talks/resources/PresIRT.pdf
http://www2.uaem.mx/r-mirror/web/packages/mirt/vignettes/mirt-presentation-2012.pdf
Hi Björn Hommel ;
you can use sirt package for this purpose. DETECT and Noharm tests can be conducted with sirt package. You can use expl.detect() function for DETECT method and noharm.sirt() function for NOHARM method.
Hope helps.
AFK
Forget ltm and switch to mirt. You can use full information item factor analysis which uses the marginal maximum likelihood estimator. You may then extract one latent trait and then more in an exploratory mode and then compare the models with the information criteria via the anova function.
Article Validation Instrument to Evaluate Students' Perception of Vi...
It was explained in detail.
Dear Björn Hommel,
Mokken scaling techniques are a useful tool to construct unidimensional tests or use questionnaires that comprise multiple binary or polytomous items.
To assess it :
{R} Monotonicity using ‘mokken’
require(mokken)
coefH() # Check the Loevinger’s H value (>3 is ok, >5 is excellent)
aisp() # Check the unidimensionality
- Badges
- Science topic
- Similar topics
- Psychology
- Psychometrics