February 2012


Options: Use Monospaced Font
Show Text Part by Default
Condense Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
text/plain; charset=windows-1252
Carlotta Domeniconi <[log in to unmask]>
Mon, 27 Feb 2012 18:57:08 -0500
1.0 (Apple Message framework v1084)
Carlotta Domeniconi <[log in to unmask]>
text/plain (44 lines)
We will be holding a Seminar on Bayesian Inference at GMU on Tuesday, March 20. The presenter is John White, a PhD student at Princeton. The seminar outline and a bio of the presenter are shown below. There will be two three-hour sessions: from 9AM till noon and from 1PM to 4PM.

If you are interested in attending please let me know by March 1. This will allow us to get an idea of the necessary room size. 


Here is the seminar outline:

Section 1: An Introduction to Bayesian Inference
- Introduce the Bayesian paradigm of inference as probabilistic calculation
- Provide a loose treatment of the Cox axioms
- Discuss useful statistical theory:
 - Likelihood functions
 - Maximum likelihood estimation
 - Fisher information
 - Bias, variance, consistency and the Central Limit Theorem for estimators
 - Review standard probability distributions
- Go through the classical coin-filpping example in detail with a beta prior
- Describe results of Bayesian inference as comparable to MLE with regularization added in

Section 2: BUGS as a Tool for Automating Bayesian Inference
- Describe how to specify models using BUGS language
- Go through many example models
 - Normal with unknown mean, known variance
 - Normal with unknown mean, unknown variance
 - Linear regression: unknown coefficients and variance, Normal priors
 - Linear regression with Laplace priors
 - Logistic regression
 - Hierarchical models
 - LDA
 - SNA models

Section 3 (Optional): Implementing Samplers and MCMC by Hand
- Introduce the Ising model as a canonical distribution for sampling
- Review sampling techniques:
 - Rejection sampling
 - Slice sampling
 - Metropolis-Hasting sampling
 - Gibbs sampling

John Myles White is a Ph.D. student in the Princeton Psychology Department, where he studies how humans make decisions both theoretically and experimentally. Along with the political scientist Drew Conway, he is the author of a book recently published by O’Reilly Media entitled “Machine Learning for Hackers”, which is meant to introduce experienced programmers to the machine learning toolkit. John is now working with the statistician Mark Hansen on a book for laypeople about exploratory data analysis. He is also the lead maintainer for several popular R packages, including ProjectTemplate and log4r.