Specifying a categorical variable PreviousNext
Mplus Discussion > Structural Equation Modeling >
 amal khanolkar posted on Wednesday, August 15, 2012 - 6:41 am

I have the following model which I'm trying to run. Its a fairly simple SEM that's running well, but however the variable conscript_office is categorical (with 5 categories). Mplus now seems to treat it as a continuous variable as I get just one estimate for the regression between systolic blood pressure (syst) and conscript_office.

How do I specify that conscript office is indeed a categorical variable with 5 categories? And do I need to change the model command as well?


syst on bmi;
syst on bwtgestage_sd;
syst on education;
syst on conscript_office;
syst on age;

bmi on bwtgestage_sd;
bmi on education;
bmi on conscript_office;
bmi on age;

bwtgestage_sd on education;


 Linda K. Muthen posted on Wednesday, August 15, 2012 - 12:20 pm
Conscript_office is a covariate. Covariates can be binary or continous and in both cases they are treated as continuous. If conscript_office is nominal, you need to create a set of dummy variables. If it is ordinal, you can leave it as it or create a set of dummy variables.
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