Title: Applied Bayesian Astronomy [Lecture 3/3]
Speaker: Aaron Robotham, ICRAR (aaron.robotham AT uwa.edu.au)
Date: 1pm (AEDT) Wednesday 23rd October 2013
Abstract: Having established a grounding in R, Bayes theory and the main concepts surrounding computational Bayesian techniques (in particular, Markov chains for exploring posteriors, and Metropolis-Hastings as a Monte-Carlo Markov-Chain -aka MCMC- method), in this lecture we go on to explore how we would combat real astronomical problems. This will cover constructing realistic mock survey data from a luminosity function, and using Bayesian techniques to recover the input parameters. By the end of the lecture you should be confident enough to describe arbitrarily complicated problems using the toolkit we’ve gradually put together.
Additional Material: Talk slides are available for download here.