

Intercept for latent variable 

Message/Author 


Hi, I have a model which structurally looks like this: ... TYPE=RANDOM; ALGORITHM=INTEGRATION; MODEL: f1 BY x1x3; f2 BY y1y3; f1sq  f XWITH f; f2 ON f1 f1sq; So this works fine and both f1 as well as the quadratic term f1sq load on f2. What I want to do now is draw a simple graph with a line given by a function like f(x)=a + bx + cx². I assume that the estimates that Mplus provides for regressing f1 and f1sq on f2 give me the b and c respectively. But I don't seem to be able to obtain an intercept, i.e. the "a" for my f(x). I succeeded producing a nice scatter plot from the data using the PLOT3 command but I would also like to show a simple curved line showing the relationship between f1 and f2. Your help is greatly appreciated. 


In a crosssectional model, the intercept of a factor is zero. 

Back to top 

