I am working with data from psychotherapy sessions, which is nested in three levels: speaking turns nested into sessions, nested into patients.
I thought of fitting a multilevel model (MLM), since I have predictors both at the speaking turns level (therapist intervention) and at the sessions level (therapeutic alliance). However, I am also interested in modelling person-specific dynamics, so I would like to use the Group Iterative Multiple Model Estimation (Gates & Molenaar, 2012). I have been searching for information, but I have not found any indications on how to fit predictors at different levels.