BIC index PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
 cathrine pettersen posted on Tuesday, September 18, 2012 - 3:15 pm
Hello, :-)

I am comparing two models that are
based on the same sample size.
Each has 29 indicators (categorial, 5 point scale)
The only element that changes between the two models is the number of latent factors (two versus four).
I am considering using BIC, but to determine which of the models provide a better fit (i.e., I would use it as a supplement to a number of other fit indices), would it be correct to say that(a) absolute cutoffs are unneccesary in this context and (b) that because both models are based on the exact same sample size, there is no reason to use SSBIC?

 Linda K. Muthen posted on Wednesday, September 19, 2012 - 11:41 am
I would simply use BIC even if the sample sizes are the same.
 cathrine pettersen posted on Wednesday, September 19, 2012 - 1:41 pm
THank you. :-)

Can I obtain BIC values in Mplus WLSMV estimator?

 Linda K. Muthen posted on Wednesday, September 19, 2012 - 3:43 pm
No, BIC is available only with maximum likelihood estimation.
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