Order of binary and categorical varia... PreviousNext
Mplus Discussion > Structural Equation Modeling >
 MBH posted on Sunday, March 23, 2014 - 6:30 pm
Dear all,

I have a couple of questions that I cannot seem to find the answer to.

For binary and categorical variables to be used in SEM, do they need to be in a particular order for Mplus?

Question 1 - My categorical variables are not measured on a likert scale but say I have a variable that assesses education (1: primary school, 2: high school, 3: university). If I want to include it as an indicator of latent variable "socioeconomic status." does it matter what order the variables are in?
Presumably, university then becomes a measure or a high socioeconomic status? And if the order was to be reversed then primary school becomes is measure of low socioeconomic status? Am I correct in assuming this is what Mplus will assume if we ask those questions?

Question 2 - Do categorical variable need to be in 1,2,3,4 etc order or do they need to be 0,1,2,3 etc?

Question 3 - And is that also they case for binary (0: no education, 1: high education) or (0: high eduction, 1: no education). Or does the order not matter?

Thank you so much
 Linda K. Muthen posted on Monday, March 24, 2014 - 8:18 am
The order of the categories do not matter as long as as the categories of an ordinal variable go from low to high or high to low. You need to interpret the results based on the order.

If categorical variables do not have 0 as the lowest category number, Mplus recodes them. See the CATEGORICAL option in the user's guide.
 MBH posted on Monday, March 31, 2014 - 5:18 pm
thank you so much
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