Syntax for Multilevel Latent Profile Analysis - Creating teacher profiles

[Marinka Willemsen]

Dear Statalisters,

I want to identify profiles of (early childhood) teachers in our data based on 5-10 indicators on implementation readiness. It concerns multilevel data, that is, on the first level we have the child (language and literacy measures, but also implementation fidelity/adherence), second level we have the teachers, and on the third level we have the daycare centres. In creating teacher profiles, we are adopting a person-centered approach to acknowledge intra-individual variation in organizational implementation readiness. Therefore, I want to perform Latent Profile Analysis, but also take into account the multilevel structure.

Thus far I haven't seen the possibilities to do this in STATA, but since I am relatively new to STATA, I would like to know if there are any possibilities.

This earlier thread discussed my question to some extent, but then for Latent Class Analysis, which did not turn out to be the best solution for that specific research question + a user suggested to open a separate thread.

I would really appreciate any suggestions/leads/do-files to perform this kind of analysis.

Kind regards,
Marinka

[Sam Duncan]

Dear Marinka,

I wonder if you have already found an answer to your question about using multilevel latent profile analysis in Stata.
I'm struggling with a very similar thing here.
If so, can you please explain your findings here with eventually your syntax and outcomes?

Thank you so much in advance,

Sam

[Marinka Willemsen]

Dear Sam,

Finally I found that Mplus was more suitable to evaluate Multilevel Latent Profile Analyses, you could also look in to:
Mäkikangas, A., Tolvanen, A., Aunola, K., Feldt, T., Mauno, S., & Kinnunen, U. (2018). Multilevel latent profile analysis with covariates: Identifying job characteristics profiles in hierarchical data as an example. Organizational Research Methods, 21(4), 931-954.

Best,
Marinka