Person-related selection bias in mobile sensing research: Robust findings from two panel studies.

Abstract

In psychology, mobile sensing is increasingly used to record behavior in real-life situations. However, little is known about the selectivity of samples participating in these new data collection approaches and thus about potential risks to the validity of research findings. We therefore investigated two potential sources of selection bias in smartphone-based data collections. Specifically, we examined whether smartphone system ownership (Android vs. iOS, i.e., platform-related differences) and willingness to participate (nonparticipation vs. intention to participate vs. actual participation, i.e., nonresponse error) are associated with sociodemographic, socioeconomic, and personality characteristics. Using two large-scale panel studies, we found replicable patterns for platform-related differences (N = 1,218 and N = 5,123) and nonresponse error (N = 1,673 and N = 2,337): The ownership of Android devices (in comparison to iOS devices) was associated with lower levels of education, income, and extraversion. The willingness to participate in mobile sensing studies was found to be higher among younger age groups, males, those with higher levels of openness to experience, and those with lower levels of neuroticism. Furthermore, different person characteristics played different roles at different stages of the recruitment process. Taken together, the results show that some selection bias in mobile sensing studies exists and that the effects were small to moderate in magnitude as well as comparable to selection bias for other, more common data collection approaches, such as online surveys. (PsycInfo Database Record (c) 2026 APA, all rights reserved).