Most helpful thing I ever learned about Bayesian statistics came from Kant: all of a sudden the "prior" and "posterior" were easy to remember. In his introduction, he discusses the origin of synthetic knowledge, and sets about distinguishing between a priori and a posteriori knowldge: that which one had before, and that which one has after. Of course we all know about "a priori" but I had never associated "a posteriori" with the same line of thinking.
Sweet! Bookmarked. Thanks for sharing. I'm just getting started with Python and this will indeed serve as a great resource once I start delving in Data Science stuff.
If/when you start delving into Data Science stuff, you should check out Data Science Weekly http://datascienceweekly.org/ (I'm co-editor) which is a free newsletter of data science articles, blog posts, job postings, resources, and interviews with data scientists.
I love how every day there is a new post about R and statistical data analysis. It's really a hot topic. I hope somebody could upload a course using measure theory for the ones like me interested more in the abstract probability concepts.
I use R for my statistical programming mostly, but I use Python for a lot of other things. It's nice to have this as a reference when I don't feel like moving back to R.
Awesome to have this page. I was wondering about this only few days back, if I could find a website where I could learn Statistical Data Analysis in Python. :)
For those interested in this topic, I just finished and highly recommend http://shop.oreilly.com/product/0636920023784.do. It covers IPython, NumPy, Pandas and matplotlib. It doesn't cover algorithms and analysis so much, but it's great for learning the tools if you already know the statistics.
