Two new preprints on hidden multilevel Markov models | R bloggers

Hidden Markov Models (HMMs) are powerful models to capture the complex behavior of psychological processes that switch between different latent states. Examples include manic and depressive states in bipolar disorder, states of recovery and relapse as seen in addiction, and “normal” and “depressed” mood states in depressive disorders. In addition to empirically detecting latent mood/behavioral states, each associated with different subjective experiences, HMMs model the tendency to switch between different latent states over time. For example, inferring the probability of remaining in a depressive state or switching to a manic state from one moment to the next. This is something that commonly used models (e.g. autoregressive models) cannot do. Emmeke Aarts and I have two new preprints on multi-level HMMs: in the first (https://osf.io/preprints/psyarxiv/prm3t_v1) we provide a friendly introduction to multi-level HMMs and a fully reproducible tutorial on model specification, estimation, selection and interpretation of the EMA dataset for emotion time series. In the second (https://osf.io/preprints/psyarxiv/b5mxk_v2), we conduct an extensive simulation study to evaluate whether existing software works as intended and how well multi-level HMMs can be estimated in typical time series designs in psychology.

Related