11 December 2012
Review: The Signal and the Noise: Why So Many Predictions Fail - But Some Don't
The Signal and the Noise: Why So Many Predictions Fail - But Some Don't by Nate Silver
My rating: 4 of 5 stars
Nate Silver became a household name for good in this past election season thanks to his FiveThirtyEight blog, which relies on some complicated statistical analysis carried over from Bayesian theories as well as his work with Baseball Prospectus. Naturally, he wrote a tome of a book about statistics, and it's about as excellent as you would expect.
The book is mainly about statistics and probability. A lot of history of different perspectives from sports and science and even gambling is where the book finds most of its strengths, and as a person who loves data and can't get enough of it, it's got plenty of (but could have used more) graphs and information to help bolster the information. It's not too heavy, and it's not too light, either - at least for me, it hit the sweet spot of both what I was looking for and what I could handle. Very readable and very interesting.
If there are any drawbacks, it might be that his sources leave a lot to be desired in some areas, especially in issues of political import. Someone who knows a lot about the topic might find this too light. Someone expecting a political treatise will certainly be disappointed.
With all that said, however, it's a solid entry in the social/popular science books, and it's a good reminder as to what I like about Silver and his analysis.
View all my reviews