Multi-group SEM PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Ali posted on Thursday, November 05, 2015 - 2:00 am
Hello, I am running SEM for multi-group comparison.

I have three latent variables, which A,B,and C. In the latent variable C, items are forced choice. In the model, D is a manifest variable with 5 math plausible values. So, the SEM model is A->B->C->D.

I want to compare the model with 11 countries.Could you please let me know how to use my SEM model to compare 10 countries ?Because I want to know if there is any differences between countries? Also, because of five plausible values, should I run five times for the model? or there is any way to deal with five plausible values?

Thank you
 Bengt O. Muthen posted on Thursday, November 05, 2015 - 4:21 pm
First you want to study measurement invariance across the countries - see the UG and also our MI web page: http://www.statmodel.com/MeasurementInvariance.shtml

Analysis with 5 plausible values uses

DATA:
Type = Imputation;

See also the UG.
 Ali posted on Thursday, November 26, 2015 - 1:31 am
In my model, I have the forced-choice item and I transformed the data to the binary data based on Brow & Maydeu-Olivares's paper (2012).
Then, I have to do measurement invariance on the this item. Is it possible to do measurement invariance on the forced-choice item ?
 Bengt O. Muthen posted on Thursday, November 26, 2015 - 6:35 pm
I am not familiar with that work - you may want to ask on SEMNET.
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: