I am interested in examining a mediated model where the mediator is a set of 5 latent profiles derived from three continuous indicator variables. I am also interested in calculating indirect effects (e.g., Asparouhov & Muthen, 2015; Muthen, 2011) and I was hoping to use an auxiliary variable approach so that the X and Y variables do not affect the latent profile solution. The citations mentioned above make mention of such a model, as does at least one post I could find here; however, I could not find Mplus code that goes along with such a model, and I cannot figure out how to use the existing auxiliary variable techniques to specify the model correctly.
So, I suppose the first question is whether the model as I described it can be specified, but assuming that some sort of latent profile mediation model can be specified, do you know where I could find Mplus code examples for it?
I don't think there is other work to draw on yet, but you can certainly piece it together. I think Muthen (2011) has code or at least code suggestions for a latent class/nominal mediator. And stepwise mixture modeling with covariates and distals can be done as shown in Section 3.2 of the paper on our website:
Asparouhov, T. & Muthén, B. (2014). Auxiliary variables in mixture modeling: Using the BCH method in Mplus to estimate a distal outcome model and an arbitrary second model. Web note 21.