|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
The sign of a latent variable |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
|
Is there a way in Mplus to model a two-class categorical latent variable corresponding to the sign (negative/non-negative) of an existing continuous latent variable? The more general goal is to estimate a connected piecewise linear latent variable regression using cross-sectional data. |
|
|
I can't think of a way to do that. At the most the sign of the latent variable mean in the two classes can be restricted. |
|
Back to top |
|
|