I can now bring some light into the dark myself:

1) normally it is no problem to deal with missing data in ESEM. You use the FIML Estimator and everything is fine. But in my case I have a binary result. This means that I have to use numerical integration (which is needed for ML). I could avoid this with Estimator = Bayes, but this is not allowed for ESEM. So I have to stay with WLSMV - but this estimator uses listwise deletion.

2) My solution is to:

first create new datasets by multiple imputation as described in example 11.5 of the User Guide and:

then calculate them with Estimator = WLSMV.

3) Answers/opinions are welcome.

Dear Stefan Poier,

How can Mplus handle missing data in ESEM with rotation target? As I don't completely understand the issue that you have raised for discussion, please make some clarifications of the issue so that we wil lbe able to understand it and to follow the disucssion. If that is accomplished we will then be able to make a contribution in the discussion.

Best Regards

Desalegn Abraha

Dear Desalegn Abraha,

thank you for your interest in the topic.

I wondered why I had a listwise deletion of cases with missing data in my calculation (ESEM with EFA factors, Mplus). The reasoon was:

Normally - using FIML estimation - these cases are not completely excluded.But in my case I had a binary outcome. This requires numerical integration. Unfortunately Estimator = Bayes is not allowed with EFA Factors. Therefore only a calculation with Estimator = WLSMV was possible. So: Mplus can handle missing data in an ESEM well - but unfortunately not with binary outcome.

Best regards

Stefan