Sara Suzuki posted on Tuesday, September 10, 2019 - 11:32 pm
Say I have a GMM with variables a and b, and an LTA with variables d and e. It's all from the same dataset. Can I relate the GMM classes to the LTA patterns? Maybe a simple cross-tab of the modal classes? What are potential problems with this approach?
You can do a cross-tab using Most Likely Class if you have high entropy (say larger than 0.8).
See also this paper:
Nylund-Gibson, K., Grimm, R., Quirk, M., & Furlong, M. (2014): A latent transition mixture model using the three-step specification. Structural Equation Modeling: A Multidisciplinary Journal, 21, 439-454.