Residual Covariances (Cate/Cont) PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 Martin Schultze posted on Tuesday, March 07, 2017 - 4:49 am
Is there any way to allow for local dependence in LPA/LCA with both, continuous and categorical indicators? From what I've gathered there is parameterization=rescov; to allow for residual covariances between categorical indicators and the normal "with" command to allow for covariances between continuous indicators. Trying to allow for the covariance between a continuous and a categorical indicator returns a fatal error. Is there any working alternative in Mplus to allow for these residuals as well?
 Bengt O. Muthen posted on Tuesday, March 07, 2017 - 6:23 pm
You have to put a factor behind those 2 indicators like we do in UG ex7.16.
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