Unfortunately I have not been able to find the answer to my question elsewhere, so here goes:
I have recoded my data into categorical variables which (-1 for low scores, 0 for average, 1 for high). I can't for the life of me figure out how Mplus decides which category is which; I get .gph output for only 2 and 3, but whether those are 0/1 or another combo I can't tell for sure. I would assume it starts with the lowest value (in this case -1) but I can't confirm this myself.
Also, when I (assuming 2=0 and 3=1) try to calculate probabilities for -1 by doing 1-prob2-prob3, I sometimes get negative values, meaning that (prob2+prob3)>1, which should be impossible.
I would very much appreciate any help pointing out what mistakes/wrong assumptions I'm making.
I'm unable to find the section you are referring to. Is it a subsection of the chapter on LCA?
I found this in example 7.3
"The CATEGORICAL option is used to specify which dependent variables are treated as binary or ordered categorical (ordinal) variables in the model and its estimation. In the example above, the latent class indicators u1, u2, u3, and u4, are binary or ordered categorical variables. The program determines the number of categories for each indicator."
But that doesn't tell me much.
Could you please help me out by referring me to a chapter or page?
If you keep reading, you will see how the variables are recoded. They are not analyzed as -1, 0, 1. If there is something in an output you don't understand, send the output and your license number to email@example.com.