Multigroup SEM, complex data, and 3 c... PreviousNext
Mplus Discussion > Categorical Data Modeling >
 Kathleen Shakira Washington posted on Thursday, July 06, 2017 - 1:36 pm
I am attempting to run a multigroup SEM on a complex data set that includes three categorical outcome variables. I keep getting error messages. I have included most of my syntax below. Any assistance would be appreciated.

categorical = distress behavior suicide;
missing = all(-999);
weight = WEIGHT;
strat = STR;
cluster = SECU;
grouping = ACE2_G7 (0=ACE0 1=ACE1 2=ACE2
analysis: type = complex;
estimator = MLR;
model: Religion by...;
Family by ...;
Friend by ...;
Teacher by ...;
School by ...;

Distress ON Age GENDER POVERTY...;
Behavior ON Age GENDER POVERTY...;
Age GENDER POVERTY PAR_EDUC US_CIT O_DSM Black Hispanic Other Metro O_Urban WITH Religion Family Friend Teacher School;
Distress WITH Behavior;
Distress WITH Suicide;
Behavior WITH Suicide;
model ACE1;
model ACE2;
model ACE3;

output: modindices standardized;

*** ERROR in ANALYSIS command ALGORITHM=INTEGRATION is not available for multiple group analysis. Try using the KNOWNCLASS option for TYPE=MIXTURE.
 Linda K. Muthen posted on Thursday, July 06, 2017 - 5:38 pm
When you use maximum likelihood with categorical dependent variables, numerical integration is required. The GROUPING option is not available in this case. Multiple group analysis is done with TYPE=MIXTURE and the KNOWNCLASS and CLASSES options. When all classes are known, it is the same as multiple group analysis.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message