|
Abstract:
|
The last decades have seen a steady growth in enthusiasm for dynamical systems as a means for characterizing change mechanisms in the social, behavioral and health sciences. This is due, in part, to the success of dynamical systems approaches for discerning the dynamics embedded in intensive longitudinal data from wearable devices, smartphones, sensors, online behavioral data, and GPS systems. In this presentation we use examples from these intensive longitudinal data to demonstrate ways to expand initial model building and exploratory results to allow for subsequent confirmatory model fitting and inference. . Practical guidelines, recommendations, and software code for exploring and fitting deterministic and stochastic dynamical systems models with linear and nonlinear change functions are provided along with some cautionary notes, challenges, and unresolved issues in utilizing these techniques.
|
