Degrees of freedom in multilevel anal... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
 Kathrin Eck posted on Monday, January 19, 2015 - 6:57 am

For different multilevel analysis (mediation, moderation and moderated mediation) I need to report the degrees of freedom in my master thesis.

Can you please tell me with which MPlus-command I get them? Or are there formulas to compute them?

Thank you for your reply!
 Bengt O. Muthen posted on Monday, January 19, 2015 - 9:00 am
If you don't see df I think you have categorical or count outcomes where chi-2 testing is not available.
 Kathrin Eck posted on Monday, January 19, 2015 - 9:44 am
Thanks for your quick reply!

I have continous variables. I guess, I work with Version 7.1. In some outputs I get information about the chi-2 test and its df, in others not.

For example this cross-level-interaction testing comes without df:

analysis: type = twolevel random;

model: %within%
spl1| PA_tag on PL_tag;

[spl1] (spl1_mw);
PA_tag on NA_trait;
spl1 on NA_trait; !interaction;

Do you have any idea how to get the df?
Thanks for your help!
 Bengt O. Muthen posted on Monday, January 19, 2015 - 10:38 am
Type=Random is another case where chi-2 is not available. This is because random slopes produce varying variances as discussed in our video and handout for Topic 7, slide 46.

Different H0 models can still be compared using BIC as well as chi-2 based on logL differences.
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