# By the books...

Most of the applications of Bayesian methods I've encountered and used to date are in the areas of text mining and machine learning, such as topic modeling using LDA models, naive bayes classifiers, and in time series analysis (Kalman filters and state space models). But I have employed these largely as gray box solutions to specific problems I've faced. I want to develop an understanding of the Bayesian framework that allows me to apply it to all the problems to which I would apply my traditional maximum likelihood based modeling toolkit. In order to really master these tools, I am going to work through some basic statistical problems using them. To get these problems to work through, and to have references along the way, I'm going to be using a number of textbooks, as I have obsessively and expensively amassed quite a little collection. In perusing them all and working through the introductory chapters of each, I've decided on three of them as the core of my 'curriculum':

- Introduction to Bayesian Statistics, William Bolstad
- Doing Bayesian Data Analysis, John K Kruschke
- Bayesian Data Analysis, Andrew Gelman, John B. Carlin, Hal S. Stern and Donald B. Rubin

The first book is a true introductory textbook, whose audience is first-time statistics students. It aims to introduce probability and statistics in a Bayesian framework. Kruschke's book is great for the practical R and BUGS code, and is entertainingly written, and Gelman's book has a lot of great detail on distribution theory and social science examples that have more immediate traction in my brain. I think between the three, I will be able get anything I could want from a textbook on bayesian statistics. Well...not anything...but no textbook can actually provide that...

[...] and of course the Bolstadt, Kruschke and Gelman books and the work of John Myles White mentioned in my initial post here. [...]