I am conducting a cfa (two level, with meaning of level 2;it is staff rating organizations and we care about organizations).

My question is what is the difference is in mplus between type=complex (mlr with sandwich) and type=twolevel if mlr is selected as an estimator with no covariates in the model?

These should be the same corrct?


If you care about the organizations (the clusters), then use type=twolevel and estimate a within and a between part of your model.

If you were not concerned about the clustering level but wanted to control for within-cluster correlation (you should do that), you would use type=complex to make Mplus use a sandwich estimator.

These two solutions are different in that they will estimate different models (two-level vs single level), and you can expect that they will produce different results for the within part (which would be the only part estimated if you use type=complex model).

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.