Chi Square Multilevel for categorical... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Adel Pwell posted on Tuesday, August 13, 2013 - 7:45 am
I imported data for categorical multilevel model just like I did for my continuous model so I could get all the Chi Square information. For continuous data after reading in the list.dat file I was able to get the chi square values for all estimators. However, for categorical data I am not able to obtain the chi square values for the ML estimators.
 Linda K. Muthen posted on Tuesday, August 13, 2013 - 7:54 am
Chi-square and related fit statistics are available only when means, variances, and covariances are sufficient statistics for model estimation. This is not the case with categorical variables and maximum likelihood estimation. You can try using the WLSMV estimator if you want these fit statistics.
 Adel Pwell posted on Tuesday, August 13, 2013 - 8:07 am
Thanks.

Chi-square and related fit statistics are available only when means, variances, and covariances are sufficient statistics for model estimation


If a multilevel model uses means at the between level and I have categorical data then what is it looking at instead of means? Some fit indexes do print but just not Chi Square.
 Linda K. Muthen posted on Tuesday, August 13, 2013 - 9:06 am
The model is fit to the raw data not the means, variances, and covariances. Nested models can be compared using -2 times the loglikelihood difference which is distributed as chi-square.
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: