Presented by:Brian Blais, Bryant University
Bayesian analysis is fast becoming the de-facto approach for modern analysis and big data. However it has not made much of an impact in the introductory undergraduate and high school level - the typical "Stats 101". Part of this difference comes down to mathematical sophistication needed to do proper Bayesian analysis. However, with approximate methods and computational methods, the Bayesian perspective can be presented at the introductory level. This poster describes one such project to do that, including approximations to statistical tests and some simple Markov Chain Monte Carlo (MCMC) simulations accessible to undergraduates. The core of the computational component uses the iPython Notebook, which provides the perfect framework with which to do open and sophisticated numerical analysis.
(Tip: click the fullscreen control)
Having trouble viewing? Try: Download (.mp4)
(Tip: right-click and choose "Save As...")