LTA FOR TWO TIME POINTS WITH A COVAR... PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
Message/Author
  nuoshin ahanchi  posted on Thursday, December 22, 2016 - 4:35 am
Dear Dr. Muthen,
I need to run example of a LTA for two time points with a binary covariate influencin the latent transition probabilities using example EXAMPLE 8.13
I got the following errors:
*** WARNING in VARIABLE command
Variable G, used in KNOWNCLASS specification, has been removed from the
USEVARIABLES list. Subsequent errors may occur if this variable is used
elsewhere.
*** ERROR in OUTPUT command
Unrecognized option for OUTPUT:
TECH15
  nuoshin ahanchi  posted on Thursday, December 22, 2016 - 4:41 am
Dear Dr. Muthen,
I'd appreciate your advice on specific changes I need to make to this input:
NPUT INSTRUCTIONS

TITLE: this is an example of a LTA for two time
points with a binary covariate influencing
the latent transition probabilities
DATA: FILE = pooldatadorost.dat;
VARIABLE: NAMES = u11-u18 u21-u28 g;
CATEGORICAL = u11-u18 u21-u28;
CLASSES = cg (2) c1 (4) c2 (4);
KNOWNCLASS = cg (g = 0 g = 1);
ANALYSIS: TYPE = MIXTURE;
MODEL: %OVERALL%
c1 c2 ON cg;
MODEL cg: %cg#1%
c2 ON c1;
%cg#2%
c2 ON c1;


*** WARNING in VARIABLE command
Variable G, used in KNOWNCLASS specification, has been removed from the
USEVARIABLES list. Subsequent errors may occur if this variable is used
elsewhere.
*** ERROR in OUTPUT command
Unrecognized option for OUTPUT:
TECH15
 Bengt O. Muthen posted on Thursday, December 22, 2016 - 10:11 am
Please send your output and license number to Support along with your license number.
  nuoshin ahanchi  posted on Friday, December 23, 2016 - 10:26 pm
Dear Dr. Muthen & Muthen,
Thank you very much. Sending output file attachment for you.
Analyses were conducted using Mplus version5.
 Linda K. Muthen posted on Saturday, December 24, 2016 - 11:09 am
This option was not available until after Version 5.
  nuoshin ahanchi  posted on Friday, January 27, 2017 - 11:23 pm
Dear Drs. Muthen,
Thank you very much for your answer

I need to run example of a LTA for two time points. in both time1and time 2, we selected the four-latent-class model.
I am register in www. stat model.com.I conducted with mplus version7.4
4-class LTA Model with measurement noninvariance

LATENT TRANSITION PROBABILITIES BASED ON THE ESTIMATED MODEL

C1 Classes (Rows) by C2 Classes (Columns)

1 2 3 4

1 0.000 1.000 0.000 0.000
2 1.000 0.000 0.000 0.000
3 0.000 0.000 1.000 0.000
4 0.000 0.006 0.000 0.994


4-class LTA Model with measurement invariance


C1 Classes (Rows) by C2 Classes (Columns)

1 2 3 4

1 1.000 0.000 0.000 0.000
2 0.000 0.764 0.218 0.018
3 0.000 0.000 1.000 0.000
4 0.091 0.000 0.073 0.836

please advise me about my result.
  nuoshin ahanchi  posted on Friday, January 27, 2017 - 11:29 pm
Dear Drs. Muthen,

note(( Structural Equation Modeling
Applications Using Mplus)
we selected model measurement noninvariance,but confused with seen result.

1 2 3 4
1 0.000 1.000 0.000 0.000
2 1.000 0.000 0.000 0.000
3 0.000 0.000 1.000 0.000
4 0.000 0.006 0.000 0.994


plese advise me
 Bengt O. Muthen posted on Saturday, January 28, 2017 - 11:26 am
You should base your decision about measurement invariance or not using BIC or difference testing using likelihood-ratio chi-square.

With non-invariance you don't know if the transitions you are considering refer to classes with the same substantive meaning.

With non-invariance the class order may be different - perhaps class 1 and 2 are switched between the two time points. If so, it looks like everyone stays at the class they started in.

For further interpretations matters, you may consult SEMNET.
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: