Nominal and categorical variable PreviousNext
Mplus Discussion > Structural Equation Modeling >
 MBH posted on Tuesday, April 29, 2014 - 8:06 am
Dear Linda,

I read your reply to one of the question regarding regression in SEM after adjusting for age and sex with great interest, in which, you provided the following syntax:

If you factor is iv, the BY statement should be

Then you can regress iv on the covariates:
iv ON age sex;

Sex appear to be nominal rather than categorical and if sex is not specified as categorical within the model because it is an independent variable then model produces the output without a problem.

However, if sex is specified as categorical then Mplus gives following message: "The following variable is an independent variable in the model. Problem with: SEX"
- This is where sex is not dependent on any other variable within the model.

And when specified as nominal then the following message is given: "A nominal variable may not appear on the right-hand side of an ON statement: SEX"

So my question is it acceptable to not specify sex as either categorical or nominal variable in the SEM model and adjust for it or is it better to specify it as categorical or nominal and then adjust for it? and if so then what is the best method to deal with the warnings produced by Mplus?

Thank you
 Linda K. Muthen posted on Tuesday, April 29, 2014 - 9:50 am
The scale of observed exogenous variables is not considered in regression. These variables can be binary or continuous. They are treated as continuous in both cases. They should not be put on the CATEGORICAL or NOMINAL list.
 MBH posted on Tuesday, April 29, 2014 - 11:21 am
Thank you Linda
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