Predicting the Use of Digital Health Devices during Covid-19
Data scientist in Basel
portfolio_page-template-default,single,single-portfolio_page,postid-2995,bridge-core-3.1.8,qode-page-transition-enabled,ajax_fade,page_not_loaded,,qode-title-hidden,qode_grid_1300,side_area_uncovered_from_content,overlapping_content,qode-content-sidebar-responsive,qode-theme-ver-30.5,qode-theme-bridge,disabled_footer_top,qode_header_in_grid,qode-portfolio-single-template-4,wpb-js-composer js-comp-ver-7.6,vc_responsive


Digital health

Digital devices from sensors to mobile applications are becoming increasingly important in disease prevention and diagnostics



Part of the University of Basel research in Economic Psychology


R, Stan

Realized in R-Statistics, RStan (brms), JavaScript, and Qualtrics, representative sampling via LINK

Predicting the Use of Digital Health Devices during Covid-19

In 2020, we investigated the acceptance of digital health applications against Covid-19.

We modeled the acceptance of digital health tracking applications (SwissCovid) at the time when vaccines were still unavailable, collecting novel evidence from a large, Swiss-representative sample of the infected and non-infected population. The challenge in this project consisted in tackling the variable selection in a new domain such as digital health. I addressed it using a Bayesian state-of-the-art feature selection method called projective predictive variable selection and Bayesian linear models. This allowed us to answer when and why people accept digital health applications during Covid-19.

Find the code on GitHub. You can read the press release and the scientific paper in Nature Humanities & Social Science Communications.