JOEL WONG posted on Wednesday, May 08, 2013 - 7:06 pm
I've 2 questions: 1. Is it possible to test for multivariate normality in the Mplus basic program? I know that can be done using TECH12 but I don't have the mixture add-on program, just the basic Mplus program.
2. I am comparing the model fit of 2 measurement models using MLM: a 1-factor model with 10 items nested within a 2-factor model with 5 items per factor. I think the scaled chi squared difference test I used resulted in a negative number. I read the Asparouhov and Muthen paper but I couldn't figure out the syntax to use for the strictly positive chi scaled squared difference test. What should I do? Is there another test I should?