Computation infrastructure for teaching Bayesian modeling
In this talk we will reflect on the role of computational tools and infrastructure for teaching Bayesian modeling courses for both Undergraduate and Graduate students. In particular, we will discuss our approach for preparing and delivering an elective course (4th year undergraduate and 2nd year master's students) on Spatiotemporal modeling at Duke University. This course included an emphasis on applied Bayesian modeling of temporal, spatial, and spatiotemporal processes which are particularly challenging in terms of their computational complexity. We will discuss the infrastructure we provided to support the students in the course as well as the pedagogical considerations for the topics and tools presented in the course.
|