ML-Regression with PV PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
 Svenja Rieser posted on Thursday, December 21, 2017 - 4:52 am
Dear Drs. Muthén,

I have a question regarding a note that occurs in one of my analysis.

I am running a multi-level regression analysis with 6 latent predictor variables (3 on each level). The outcome is an achievement measure which is represented by 5 plausible values. Accordingly, I am using TYPE = IMP with 5 separate data sets. My data set contains roughly 4000 individuals in 220 clusters.

At first glance, it seemed that the model ran just fine as I don't get any error messages or warnings. However, I noticed that in the output file under sample statistics there is a note saying
"NOTE: These are average results over 0 data sets."
and no sample statistics are calculated.
All other computations (regression model, fit indices etc.) seem to have worked fine. As requested, five replications have been completed and the results seem realistic.

However, as I have no idea what went wrong with the sample statistics I am also not sure how trustworthy the other results are.
When I drop two latent variables (one on each level) from the analysis the sample statistics are computed just fine and the note says that "these are average results over 5 data sets.".

I already searched the forum but didn't find an answer. Thus, I’d appreciate any suggestion on how to deal with this note. Thank you very much!
 Linda K. Muthen posted on Thursday, December 21, 2017 - 7:04 am
Please send the output and your license number to
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