SOEP Brown Bag Seminar

Maintained Individual Data Distributed Likelihood Estimation (MIDDLE) is a new paradigm for the design and analysis of research in the behavioral, social, and health sciences. The MIDDLE approach is based on the seemingly-impossible idea that data can be privately maintained by participants and never revealed to researchers, while still enabling statistical models to be fit and scientific hypotheses tested. MIDDLE rests on the assumption that data should belong to, be controlled by, and remain in the possession of participants. Since data have value, individuals can thus accumulate personal wealth by participating in science. The innovation of the MIDDLE approach is that statistical models are fit by sending an objective function and vector of parameters to each participants' personal device (e.g., smartphone), where the likelihood of that individual's data is calculated locally. Only the likelihood value is returned to the central optimizer. The optimizer aggregates likelihood values from all participants and chooses a new parameters until the model converges. The MIDDLE paradigm solves or simplifies many current problems that plague human participant research. A MIDDLE study provides significantly greater privacy for participants; automatic management of opt-in and opt-out consent; lower cost for the researcher and funding institute; a larger base of participants; and faster determination of results. MIDDLE facilitates the use of mobile devices that can enable studies to be performed while participants remain in their normal living environments, thus opening paradigm-shifting paths in the way one thinks about research methods. Furthermore, if a participant opts into many studies simultaneously, all of the studies could automatically have access to individual-level longitudinal data sharing.