Plots PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Nadra posted on Wednesday, December 07, 2011 - 3:31 pm
Variables used at each time point are latent factors... so the intercepts cannot be estimated. Does this mean there is no way to plot the expected trajectories of each class?

VARIABLE: NAMES ARE A1-A8 C1-C8 D1-D8 SCHOOL;
CLASSES = C(2);
CLUSTER = SCHOOL;
ANALYSIS: TYPE = TWOLEVEL MIXTURE;
MODEL:
%OVERALL%
F1 by A1@1 (L1);
F1 by A2*.1 (L2);
F1 by A3*.1 (L3);
F1 by A4*.1 (L4);

F2 by B1@1 (L1);
F2 by B2*.1 (L2);
F2 by B3*.1 (L3);
F2 by B4*.1 (L4);

F3 by C1@1 (L1);
F3 by C2*.1 (L2);
F3 by C3*.1 (L3);
F3 by C4*.1 (L4);

[A1 B1 C1] (i1);
[A2 B2 C2] (i2);
[A3 B3 C3] (i3);
[A4 B4 C4] (i4);

i s | F1@0 F2@1 F3@2;

PLOT:
 Linda K. Muthen posted on Thursday, December 08, 2011 - 9:49 am
Ask for TECH4 in the OUTPUT command. This gives model estimated means of the latent variables in the model.
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: