I work with on individual sequences about the verbal and non verbal behavior. The initial data is a 5 minutes videos. We split the videos each 10 seconds and annotate the verbal and non verbal behavior on each of the 30 sequences. Therefore, the design is intensive longitudinal. The coding is done with categorical scale. I have 120 individuals, therefore I have 120 categorical intensive longitudinal sequences. I would like to describe this sequence to cluster them. The goal is not to do inferential statistics. I don't have good idea to start my modelling. Can you help me?

Similar questions and discussions