Indicator normalization PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Daniel Arad posted on Saturday, October 03, 2009 - 2:07 pm
Dear Sir, Madam

I am using MPlus for an economic model with MIMIC configuration. It is similar to example 5.8 but with a single continuous latent variable and only categorical indicators("y"s). "x"s are both categorical and continuous.

My query is: if all indicators are categorical; how does Mplus deal in such a case with the normalization of the indicator?
What is the simplest way to define this in Mplus?
 Linda K. Muthen posted on Sunday, October 04, 2009 - 9:22 am
What do you mean by normalization of the indicator?
 Daniel Arad posted on Sunday, October 04, 2009 - 12:02 pm
The manual says that "the first factor loading in each BY statement" is set to 1. In my model the "normalized indicator" is a categorical indicator.

Wouldn't the latent variable then also be categorical?
 Linda K. Muthen posted on Sunday, October 04, 2009 - 5:32 pm
The metric of a factor is set by fixing the first factor indicator to one or fixing the factor variance to one. This is done the same way irrespective of the scale of the factor indicators. Factors are continuous even when factor indicators are not.
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: