Increasingly, human behavior can be monitored through the collection of data from digital devices revealing information on behaviors and locations. In the context of higher education, a growing number of schools and universities collect data on their students with the purpose of assessing or predicting behaviors and academic performance, and the COVID-19–induced move to online education dramatically increases what can be accumulated in this way, raising concerns about students’ privacy. We focus on academic performance and ask whether predictive performance for a given dataset can be achieved with less privacy-invasive, but more task-specific, data. We draw on a unique dataset on a large student population containing both highly detailed measures of behavior and personality and high-quality third-party reported individual-level administrative data. We find that models estimated using the big behavioral data are indeed able to accurately predict academic performance out of sample. However, models using only low-dimensional and arguably less privacy-invasive administrative data perform considerably better and, importantly, do not improve when we add the high-resolution, privacy-invasive behavioral data. We argue that combining big behavioral data with “ground truth” administrative registry data can ideally allow the identification of privacy-preserving task-specific features that can be employed instead of current indiscriminate troves of behavioral data, with better privacy and better prediction resulting.

In this study, we monitored 470 university students’ smartphone usage continuously over 2 years to assess the relationship between in-class smartphone use and academic performance. We used a novel data set in which smartphone use and grades were recorded across multiple courses, allowing us to examine this relationship at the student level and the student-in-course level. In accordance with the existing literature, our results showed that students’ in-class smartphone use was negatively associated with their grades, even when we controlled for a broad range of observed student characteristics. However, the magnitude of the association decreased substantially in a fixed-effects model, which leveraged the panel structure of the data to control for all stable student and course characteristics, including those not observed by researchers. This suggests that the size of the effect of smartphone usage on academic performance has been overestimated in studies that controlled for only observed student characteristics.

This paper investigates endogenous network formation by heterogeneous agents. The agents' types determine the value of linking and we incorporate spillovers as utility from indirect connections. We provide sufficient conditions for a class of networks with sorting to be stable for low to moderate spillovers; with only two types these networks are the unique pairwise stable ones. We also show that this sorting is suboptimal for moderate to high spillovers despite otherwise obeying the conditions for sorting in Becker 1973. This shows that in our sorted networks a tension between stability and efficiency is present. We analyze a policy tool to mitigate suboptimal sorting.

What is the efficacy of redrawing school attendance boundaries as a desegregation policy? To provide causal evidence on this question we employ novel data with unprecedented detail on the universe of Danish children and exploit changes in attendance boundaries over time. Households defy reassignments to schools with lower socioeconomic status. There is a strong social gradient in defiance, as resourceful households are more sensitive to the student composition of schools. We simulate the efficacy of desegregation policies and find that in areas with large levels of segregation, behavioral responses of households almost completely offset the intended effects of boundary changes.