Modeling affect dynamics : State-of-the-art and future challenges

Abstract

The current article aims to provide an up-to-date synopsis of available techniques to study affect dynamics using intensive longitudinal data (ILD). We do so by introducing the following eight dichotomies that help elucidate what kind of data one has, what process aspects are of interest, and what research questions are being considered: (a) single- versus multiple-person data; (b) univariate versus multivariate models; (c) stationary versus nonstationary models; (d) linear versus nonlinear models; (e) discrete time versus continuous time models; (f) discrete versus continuous variables; (g) time versus frequency domain; and (h) modeling the process versus computing descriptives. In addition, we discuss what we believe to be the most urging future challenges regarding the modeling of affect dynamics.