Z scores as factor indicators PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Gareth posted on Friday, August 07, 2009 - 2:16 am
I have a latent variable defined by four indicators. I have taken Z scores because they are measured on quite different scales. Using scores helps convergence.

However, one of the Z scored variables is categorical, which means I get an error message "MOST LIKELY DUE TO VARIABLE Z1 BEING DICHOTOMOUS BUT DECLARED AS CONTINUOUS."

Would you recommend using Z scores for the other three and 1/0 for this variable, or something else?
 Linda K. Muthen posted on Friday, August 07, 2009 - 7:20 am
I would not use z-scores. I would rescale the continuous variables by dividing by a constant. I would do nothing to the binary variable.
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: