Person parameters for mixture IRT models PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 Cengiz Zopluoglu posted on Wednesday, April 19, 2017 - 1:46 pm

I just want to verify something about the printed person parameter estimates in Mplus when a mixture IRT model is fitted.

To my knowledge, when a single-class IRT model is fitted and the FSCORES are requested in the SAVE command, MPLUS is printing EAP estimates for person parameters, right?

When a mixture IRT model is fitted and the FSCORES are requested in the SAVE command, is Mplus using class specific item parameters to estimate EAP for each individual based on the assigned class membership? If a two-class model is fitted and Person X is assigned to Class 2 based on the predicted class probabilities, then EAP is estimated based on the response pattern of Person X and estimated Class 2 item parameters. Is this correct?

Thanks for your time and clarification.
 Bengt O. Muthen posted on Friday, April 21, 2017 - 6:09 pm
Q1: Yes, if ML is used (as opposed to WLSMV)

Q2: Both an overall factor score and the factor score for the most likely class are presented.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message