Bayesian and ML Fit statistics PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Shin, Tacksoo posted on Monday, June 17, 2013 - 3:32 am
Bayesian analysis offers several fit indices such as PPP, DIC, BIC, Bayes factor, etc.

Among these, what can be comparable to fit statistics by ML.

PPP may be comparable to a p-value for a chi-square test of model fit, although there are some arguments. DIC may not be comparable to BIC and AIC by ML especially under small samples and random effect models, right?

Questions are,

1. How about BIC? BIC obtained from Mplus version 7 can be comparable to BIC by ML?

2. Since Bayes factor is a indicator when comparing two models, is it similar to chi-square to df ratio?
 Tihomir Asparouhov posted on Monday, June 17, 2013 - 8:57 am
DIC is very close to AIC (asymptotically /uninformative priors)

1. Yes

2. Yes
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: