Mxiture irt constraint PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
Message/Author
 Fanny su posted on Saturday, December 16, 2017 - 11:56 pm
Hello ~
In my syntax, I need to set:
1. the discrimation parameter equals to 1 for each item and each group.
2. the thresholds are the same for each group
3. only one group's factor mean equals to zero and the other is free to estimate

But I failed..., Can you help me? Thanks!

MODEL: %OVERALL%
f BY u1-u8@1;
f;
[u1$1-u8$1];
%c#1%
[f];
%c#2%
[f];
 Bengt O. Muthen posted on Sunday, December 17, 2017 - 3:50 pm
1. If by discrimination you mean the IRT "a" parameter, note that the Mplus factor loadings are equal to "a" only if the factor variance is 1.

2. See UG examples and also our Short course Topic 2 handout and video.

3. [f@0] fixes the mean in the class that you want.

If this doesn't help, send your output to Support along with your license number.
 Fanny su posted on Monday, December 18, 2017 - 9:27 pm
Thanks for your help ~
What's the difference between MODEL RESULTS & IRT PARAMETERIZATION results?
 Bengt O. Muthen posted on Tuesday, December 19, 2017 - 3:46 pm
See our Short Course Topic 2 video and handout on our website.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: