Multimodality and skewness in emotion time series.

Abstract

The ability to measure emotional states in daily life using mobile devices has led to a surge of exciting new research on the temporal evolution of emotions. However, much of the potential of these data still remains untapped. In this paper, we reanalyze emotion measurements from seven openly available experience sampling methodology studies with a total of 835 individuals to systematically investigate the modality (unimodal, bimodal, and more than two modes) and skewness of within-person emotion measurements. We show that both multimodality and skewness are highly prevalent. In addition, we quantify the heterogeneity across items, individuals, and measurement designs. Our analysis reveals that multimodality is more likely in studies using an analog slider scale than in studies using a Likert scale; negatively valenced items are consistently more skewed than positive valenced items; and longer time series show a higher degree of modality in positive and a higher skew in negative items. We end by discussing the implications of our results for theorizing, measurement, and time series modeling.

A Dynamical Systems View of Psychiatric Disorders—Theory

“…Indeed, there is evidence that, just as in tree-cover data, the intermediate state can be relatively rare. For instance, individuals show a bimodal distribution of depressive symptoms over time, being mostly either depressed or healthy rather than something in between …”

Testing similarity in longitudinal networks: The Individual Network Invariance Test.

“…As the GVAR model assumes multivariate normality, consequently the interpretation of the GVAR parameters is not straightforward (J. Haslbeck et al, 2023).…”

Unlocking nonlinear dynamics and multistability from intensive longitudinal data: A novel method.

“…In empirical studies, this can be induced, for example, when a 0-100 slider scale is used and the slider is initialized at 50. In that case, participants may be more likely to move the slider away from 50, thereby inducing bimodality in the data (Haslbeck et al, 2023).…”

“…Psychological systems, like other complex systems in nature, consist of a large number of elements interacting continuously and nonlinearly (Olthof et al, 2020, 2023). As a result, bimodality and multimodality, which means that the data distribution has two or more modes instead of only one mode in a Gaussian distribution, are the rule rather than the exception (Delignières et al, 2004; Haslbeck et al, 2023; Haslbeck & Ryan, 2022). Also, change processes are characterized by sudden changes or regime shifts, indicating the nonstationarity of the data (Helmich et al, 2020; Olthof et al, 2020).…”