Mplus Discussion >> Model fit

Topics
Last Day
Last 3 Days
Last Week
Tree View

Edit Profile


Model fit

Mplus Discussion > Latent Variable Mixture Modeling >

Message/Author

Itziar Familiar posted on Wednesday, June 22, 2011 - 8:22 am

Hi,
I'm fitting LCA models using a measure with 38 items. I keep getting the following message: THE CHI-SQUARE TEST IS NOT COMPUTED BECAUSE THE FREQUENCY TABLE FOR THE
LATENT CLASS INDICATOR MODEL PART IS TOO LARGE.

Is there an other way that I can get a x2 test to assess model fit?
thanks!

Linda K. Muthen posted on Wednesday, June 22, 2011 - 9:36 am

The chi-square test referred to is the test of the multi-way table for the categorical dependent variables in the model. It is not useful when there are more than 8 variables.

Itziar Familiar posted on Thursday, June 23, 2011 - 2:29 pm

Thanks for your response Dr. Muthen
I ran TECH 10 to get an overall bivariate log-likelihood chi-square. I have the tests value but can I get an associated p-value as well?
thanks,

Linda K. Muthen posted on Friday, June 24, 2011 - 5:02 pm

This a simply the sum of the chi-square values for all of the bivariate tables. It is meant for descriptive purposes and no p-value is available for it.