Correlation matrix with single indica... PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Richard Wonner posted on Friday, May 22, 2015 - 3:13 pm
Dear all,

I am trying to generate a correlation matrix for a publication. My model has latent and single indicator variables. Doing the SEM with MPlus works. Now I am trying to use TECH4 to generate the correlation matrix. This works as long as there are only latent variables. Now I tried to fake a latent variable from a single indicator variable and it tells me NO CONVERGENCE.

Is there a way to get a correlation matrix with combined latent and single indicator variables?

Thanks!
Richard
 Bengt O. Muthen posted on Friday, May 22, 2015 - 5:38 pm
It works to create a latent variable behind a single indicator - just say:

f by y; y@0;

This puts the y variance into f.
 Richard Wonner posted on Saturday, May 23, 2015 - 12:02 am
That worked. Thanks a lot!
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: