Public lecture: Bayesian modelling, and visualization of problems related to forecasting urban fire
Event Details
Event Contact
Event Description
- Full Description:
- In this talk I will follow in the footsteps of Denis Lindley and offer an overview of elementary statistics from an advanced standpoint. The focus will be from a Bayesian perspective and will explain what I see as the three core ideas of Bayesian statistics.
I will demonstrate how these can be applied to conventional models such as density estimation and regression and highlight some of the challenges of spatial and spatial-temporal statistical modelling. One of these challenges is the modifiable areal unit problem (MAUP) that will be explained is as a consequence of applying conventional models to spatial statistical problems.
Finally, I will give an overview of some recent advances that overcome this challenge drawing on our work on the spatial forecasting urban fires as well as other studies.
Directions to UQ
Event Tools
Share This Event
Print
Email
Share
Rate This Event
Tweet This Event
Calendar Tools
Featured Calendars
Subscribe via RSS