Measurement model - selected observed... PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Patchara Popaitoon posted on Thursday, April 28, 2011 - 8:58 am
Dear Linda,

I would like to know if there is any rules that I can follow if I want to use only some of the observed variables to form latent factor. The thing is I have about 15-20 survey items for each factor and I can't use them all to specify the model, becuase this will cause a poor fit model. Please adivse. thanks.
 Linda K. Muthen posted on Thursday, April 28, 2011 - 10:29 am
It sounds like not all of the factor indicators measure the factors well. I would do an EFA and use the factor indicators that have high loadings on their factor and low loadings on the other factors.
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: