Statistics learning recommendations

Generalities

Statistics is a fundamental tool in the social sciences, medical sciences, actuarial science and finance. Aside from being useful professionally, some of the basic concepts of statistics are also crucial to quantitative literacy.

Some of the commonly used conceptual frameworks in statistics are misguided, and expositions of statistics are affected by this. For example, the definition of "statistical significance" is in some ways arbitrary, and is often not useful in practice, but is nevertheless given a central role in many expositions.

When one is learning statistics, one is faced with a two-fold challenge:

• One wants to learn the language and concepts that are commonly used, independently of how useful they are, so as to be able to understand and communicate people who use them.
• One wants to understand the subject at a deeper level so that one knows which of the commonly used concepts are useful in which contexts.

Recommendations

Statistical intuition with real world examples

• Naked Statistics: Stripping the Dread from the Data by Charles Wheelan

• The Signal and the Noise by Nate Silver

Frequentist approach textbook

Statistics in Plain English by Timothy C. Urdan is a lucid book that's only 200 pages long. It requires no more mathematical background than high school algebra.

Bayesian statistics

Chapter 8 of The Signal and the Noise by Nate Silver gives some history of Bayesian statistics and an exposition of the basics of the subject. (Silver's book is well-worth skimming in entirety for developing statistical intuition.)

Some blog posts

• A History of Bayes' Theorem by Luke Muehlhauser
• An Intuitive Explanation of Bayes' Theorem by Eliezer Yudkowsky.
• Bayes' Theorem Illustrated (My Way) by Komponisto.

Programming and Bayesian statistics

• Think Bayes: Bayesian Statistics Made Simple by Allen Downey
• Doing Bayesian Data Analysis: A Tutorial with R and BUGS by John Kruschke.