Bayesian statistics made simple
Our workshops take a computational approach, so we avoid the math and get straight to the fundamental ideas. We focus on realistic problems with real-world complexity. And participants work hands-on, so they learn practical tools as well as the theory.
The workshops use Python, so participants should be familiar with basic Python, including classes and methods. No statistics background is required.
The first round of workshops is scheduled for Summer 2015:
July 22: Bayesian Statistics in Python I
August 10: Bayesian Statistics in Python I
August 18: Bayesian Statistics in Python II
Workshops run from 9 am to 12:30 pm, with two breaks, refreshments provided. Participants should bring a laptop running Python and related software (see Workshop Preparation below).
Sessions are limited to 15 participants to allow one-on-one interaction and troubleshooting.
Early registration is 14 days prior to the workshop. Cancellation fee any time after registration is $150 ($75 for students). If we cancel a session or reschedule to a time you cannot attend, we will refund fees in full.
Location: Downtown Boston or Cambridge, accessible by public transportation.
Accessibility: We are committed to making these workshops accessible to participants with communication disabilities. We are not experts, but we will work with you to identify effective accommodations.
Prof. Allen Downey
These workshops are developed and led by Allen Downey, a professor at Olin Collegeof Engineering, using material from his book, Think Bayes (O’Reilly Media 2013). Prof. Downey has more than 15 years of teaching experience, and has offered successful workshops at PyCon and other professional conferences.
Prof. Downey has a Ph.D. in Computer Science from U.C. Berkeley, and a M.S. and a B.S. in Engineering from MIT. Before joining Olin College, he taught at Colby College and Wellesley College. In 2009-10 he was a Visiting Scientist at Google, Inc. He is the author of several books, including Think Python, Think Stats, and Think Complexity, published by O’Reilly Media.
Participants should be familiar with Python, but no statistical background is required. Each participant should have a laptop with an Python environment that includes the SciPy stack (details below).
If possible, I encourage participants to read Chapter 1 of Think Bayes before the workshops. Electronic versions of the book are available from thinkbayes.com
Code for the workshops is in a repository on GitHub. If you have a Git client installed, you should be able to download it by running:
git clone https://github.com/AllenDowney/BayesMadeSimple.git
It should create a directory named BayesMadeSimple. Otherwise you can download the repository in this zip file:
To do the exercises, you need Python 2.x or 3.x with NumPy, SciPy, and matplotlib. To test your environment:
A window should appear with a graph of a normal distribution. If so, you have everything you need for the workshops.
Otherwise, I highly recommend installing Anaconda. By default it contains everything you need for the workshops; it is easy to install on Windows, Mac, and Linux; and because it does a user-level install, it will not interfere with other Python installations.
Information about Anaconda is here
If you have any problems, please let me know before the workshops. We will not have time on the day to debug environments.
However, if you are not able to get your environment set up ahead of time, please come to the workshops anyway. At the beginning I will pair up participants to work together. As long as each pair has a working environment, we will be all set.