Modeling the co-evolution of relational events and longitudinal survey data
Christoph StadtfeldThe increasing availability of digital behavioral trace data promises novel social science studies that simultaneously scale up on a large number of study participants and zoom in on fine-grained individual behavioral actions. These digital behavioral traces (DBTs) may, for example, stem from (social) media platforms, social sensor experiments, wearable technologies such as smart phones or watches, or a combination of these. DBTs offer a seemingly objective perspective on how people behave individually and socially – how they eat, sleep, travel, interact, socialize, and date. DBT data often come in the form of (relational) events – time-stamped monadic or dyadic observations. Several models for the statistical analysis of relational events are available and mostly build upon Carter Butts’ relational event framework and Tom Snijders’ actor-oriented models.
However, studies that merely rely on DBT data have some obvious blind spots. Individual behavior is to a large extent based on how individuals perceive their environment, their relationships, and themselves. Such perception data can best be collected through traditional surveys – despite known challenges such as cognitive burdens and time investment by participants, and measurement biases. Dynamic network data collected through surveys can, for example, be statistically analyzed with stochastic actor-oriented models or similar approaches.
To date, no statistical and computational models exist in which survey data and DBT data can be analyzed simultaneously. In this talk, we present a new framework for the joint statistical analysis of relational events and longitudinal panel data. We argue that the combination of DBT and perception data could enable new insights into the dynamics of social networks at varying time scales. The fruitfulness of this approach is illustrated in a case study that explores the co-evolution of friendship perceptions and social media connections in a panel of undergraduate students.