Recovering Within-Person Dynamics from Psychological Time Series

Abstract

Idiographic modeling is rapidly gaining popularity, promising to tap into the within-person dynamics underlying psychological phenomena. To gain theoretical understanding of these dynamics, we need to make inferences from time series models about the underlying system. Such inferences are subject to two challenges: first, time series models will arguably always be misspecified, meaning it is unclear how to make inferences to the underlying system; and second, the sampling frequency must be sufficient to capture the dynamics of interest. We discuss both problems with the following approach: we specify a toy model for emotion dynamics as the true system, generate time series data from it, and then try to recover that system with the most popular time series analysis tools. We show that making straightforward inferences from time series models about an underlying system is difficult. We also show that if the sampling frequency is insufficient, the dynamics of interest cannot be recovered. However, we also show that global characteristics of the system can be recovered reliably. We conclude by discussing the consequences of our findings for idiographic modeling and suggest a modeling methodology that goes beyond fitting time series models alone and puts formal theories at the center of theory development.

Averting the next credibility crisis in psychological science: Within-person methods for personalized diagnostics and intervention.

“…Some research areas have widely adopted some (but usually not all) within-person methods described above. For instance, a number of studies in the area of personality psychology, clinical psychology, and emotion research examine within-person variance with multi-level models and within-person network models (e.g., Beck & Jackson, 2019;Haslbeck & Ryan, 2020;Hoffart & Johnson, 2020). In contrast, in some fields of motivational psychology, research on education, and in research related to problems of personalized learning, there may still be a need for within-person approaches to complement the currently widely prevailing between-person approaches.…”

Anticipating critical transitions in psychological systems using early warning signals: Theoretical and practical considerations.

“…The notion of critical transitions between "healthy" and "unhealthy" stable states has played an important role in theoretical psychology (e.g., Borsboom, 2017;Cramer et al, 2016), and a second interpretation of our results understands the Lotka-Volterra model in this way: as an ideal dynamical system that shows critical transitions between two stable states (see also Haslbeck & Ryan, 2021;van de Leemput et al, 2014). In contrast to this ideal system, real psychological systems likely show complications that suppress the occurrence of early warning signals, as discussed in detail in a previous section.…”

“…In particular, emotions can have a positive valence, such as cheerful and content, or a negative valence, such as anxious and sad, and we might believe that there exists a tipping point in the mood system such that, when crossed, a person abruptly moves from a stable positive mood state into a stable negative mood state. To formalize such a simplified mood system, we use a four-dimensional version of the Generalized Lotka-Volterra model (e.g., van Nes & Scheffer, 2004) as our toy model: where we interpret the variables x 1 and x 2 as cheerful and content, and the variables x 3 and x 4 as anxious and sad (see also Haslbeck & Ryan, 2021; van de Leemput et al, 2014). Equation 1 describes what the rate of change of each variable x i depends on.…”

Measuring parent-adolescent interactions in natural habitats. The potential, status, and challenges of Ecological Momentary Assessment.

“…Secondly, in smart-phone applications, EMA could be combined with more precise and timely delivery of interventions [14], [16], [47]. Indeed in other domains, EMA is used to identify risk with more sensitive measures, provide tailored feedback, and identify person-specific targets for intervention [48]- [50]. Thirdly, by providing micro-insights into the underlying working-mechanisms EMA yields in-depth insights into how interventions work, why they work, and what works for whom [16], [51].…”