Chi-square =1 PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 Lorraine Ivancic posted on Monday, December 20, 2010 - 3:39 pm
I am running an LCA with 19 binary variables. When I run my LCA model the Peason Chi-square and Likeliehood ratio Chi square p-values equal 1.
I have a few questions about this:
1.Is this because I have sparse data for some of the response patterns or is it something else?
2. Can I still use this model or does the pvalue of 1 make it invalid?
3. If I can still use the model are there any other statistics I use to assess model fit?
Any help on this would be greatly appreciated. Thanks
 Linda K. Muthen posted on Tuesday, December 21, 2010 - 5:22 pm
With over eight categorical latent class indicators the Pearson and Likelihood chi-squares are not reliable due to the very large multiway frequency tables that are being tested.

The model may still be valid. You can use TECH10 to assess fit.
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