Categorical outcome and time-invaryin... PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Yang Xiao posted on Monday, November 29, 2010 - 3:19 pm
Dear Drs. Muthen,

I am trying to fit the trajactory of the categorical outcome variable defined as smoking status(csmk02-csmk04),which are ordered from 1-4,measured at year1 up to year3.
Below is my program:

DATA: FILE = 'Z:\NSPY\psu_m1.txt';
VARIABLE: NAMES = yraceeth csmk02 csmk03 csmk04 ;
usevariables = csmk02 csmk03 csmk04;
class = c(3);
!CATEGORICAL = yraceeth;
Model:
%Overall%
i s |csmk02@0 csmk03@1 csmk04@2;
!i s ON yraceeth;
Analysis:
Type=mixture;
Starts = 100 10;
Output:
tech1 tech11 ;
Plot:
type = plot3;
series = csmk02 csmk03 csmk04(*);

Now I want to see whether the trajactory is different among the three racial group(yraceeth),which is a time-invarying covariate.Could you provide an similar example in the manual of version 5?

BTW,I tried to run the code including the comments as above,which does not work.

Thanks!

Yang
 Linda K. Muthen posted on Tuesday, November 30, 2010 - 9:27 am
If you want to use the three-category variable yraceeth as a covariate, you need to create two dummy variables. You can then regress c on the two dummy variables to see if class membership is related to race and regress i and s on the two dummy variables to see if the trajectory is related to race. If you have a problem with an input file, please send the problem and your license number to support@statmodel.com.
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: