Group Iterative Multiple Model Estimation (GIMME) is an algorithm for finding models that describe dynamic processes. It is well-suited for psychophysiological (e.g., functional MRI), passively collected data (e.g., via smartphone) and ecological momentary assessments (e.g., observational coding; daily diary; intensive longitudinal data).
GIMME reliably recovers the true structure of connections and estimates the weights attributed to each relation (equivalently termed “path” or “adjacency” or “connection”). Importantly, patterns are obtained at both the group and individual levels. GIMME is one of the few approaches that accommodates heterogeneity in patterns across individuals within a sample. Both lagged and contemporaneous relations are in the search space. Currently the lag is one and the contemporaneous relations can be directed (structural VAR) or undirected (VAR).
GIMME is available as a freely distributed and actively maintained R package; gimme. Developers can access the code on our Git.
Please reference: Gates, K. M. & Molenaar, P. C. M. (2012). Group search algorithm recovers effective connectivity maps for individuals in homogeneous and heterogeneous samples, NeuroImage, Volume 63, Issue 1(15), 310-319, doi:10.1016/j.neuroimage.2012.06.026
General questions, comments, and issues can be directed to: firstname.lastname@example.org