LTA,distal outcome, and covariates PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
Message/Author
 Dylan John posted on Wednesday, September 13, 2017 - 8:31 am
I am currently running an LTA between two timepoints to look at the association of the transition groups with my distal outcome (y) of suicide attempts (dichotomous). I have two questions that pertain to my covariates (z1,z2,z3) and how to use them.

1. Does this syntax look correct (only showing 1 transition group):

model:

%overall%
x2 on x1;

%x1#1.x2#1%
[c_wave1#1@25 c_wave1#2@0 c_wave1#3@0];
[c_wave2#1@25 c_wave2#2@0 c_wave2#3@0];
y on z1;
y on z2;
y on z3;
[y$1] (thr11);

2. Some of my covariates are categorical, with k levels. Does this mean that I need to create k-1 dichotomous dummy variables. For example, race: white, black, asian, other.

dummy variable 1:
1=black
0=white

dummy variable 2:
1=asian
0=white

dummy variable 3:
1=other
0=white
 Bengt O. Muthen posted on Wednesday, September 13, 2017 - 4:38 pm
Q1: The y statements look correct, but I don't know what this means:

[c_wave1#1@25 c_wave1#2@0 c_wave1#3@0];
[c_wave2#1@25 c_wave2#2@0 c_wave2#3@0];

Q2: Yes.
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: