What: Programming with models: An introduction to NIMBLE, a BUGS-compatible system for hierarchical statistical modeling using MCMC and more
When: May 27, 2016, 10:00 am – 12:00 pm
Where: ML- VisLab
This webinar will introduce attendees to the NIMBLE system for programming with hierarchical models in R. NIMBLE (r-nimble.org) is a new system for flexible programming of algorithms that builds on the BUGS language for declaring hierarchical models. NIMBLE provides analysts with a flexible system for using MCMC, sequential MC and other techniques on user-specified models. It provides developers and methodologists with the ability to write algorithms in an R-like syntax that can be easily disseminated to users. C++ versions of models and algorithms are created for speed, but these are manipulated from R without any need for analysts or algorithm developers to program in C++. While analysts can use NIMBLE as a drop-in replacement for WinBUGS or JAGS, NIMBLE provides greatly enhanced functionality in a number of ways. The webinar will first show how to specify a hierarchical statistical model using BUGS syntax and fit that model using MCMC. Participants will learn how to customize the MCMC for better performance and how to specify one's own statistical distributions and functions to extend the syntax of BUGS. Next the webinar will demonstrate how to use other non-MCMC algorithms to fit and models. Finally, the webinar will show how to use the system to write algorithms for use with hierarchical models, including one's own samplers for use within NIMBLE's MCMC system.
The instructor is Dr. Chris Paciorek (UC Berkeley). Participation is free, but the number of seats is limited to 20. To reserve a seat, please email Kathy Peczkowicz (firstname.lastname@example.org). The format of the webinar is interactive with two-way video and audio, where the participants can ask live questions. Each participant should bring a laptop.