3 of 4 people found the following review helpful
Statistics for everyone,
This review is from: The Signal and the Noise: The Art and Science of Prediction (Paperback)
Customer review from the Amazon Vine Programme (What's this?)
Nate Silver comes with big credentials, and that's why his name is big on the front cover and not the title. After all, he is the man who succeeds in predicting election outcomes. In the first half of the book, we are treated to his preferences in life: baseball and statistics, slagging off economists, appreciating hard working weathermen, the disasters of trying to predict earthquakes, and more baseball. He goes into intricate details when it comes to baseball. He is also quite good at mentioning his successes. And others' failures. The first half of the book is strange, not really a story, not really scientific, just lots and lots of examples of people trying to predict things and the failures and successes. And lots of baseball detail.
As an aside: it shows how far the American use of the English language (or at least Nate Silver's use of it) has drifted away from British English.
In chapter 8 then we are introduced to his central tool, Bayes' Theorem. To see it applied to betting and games like chess and poker, makes for interesting reading. I must say that his informal, un writerly style of writing is an easy enough read, even so I skipped lots. You could probably learn the essentials of his approach in a book a quarter of this one's size, or less: what are the possibilities and the limits of predictions and what are the tools that can be applied. What comes out well is the importance of critical appraisal and the dangers of wishful thinking and self delusion. There are also some interesting thoughts on correlation and modelling, especially their limits.
May be it does need all those examples, and who doesn't like to read how stupid the bankers behaviour was to get into such a mess. Except, those were not stupid people, they had scientist and the best Mathematicians they could buy, and still it went wrong. Because they were interested in keeping it going, it made them rich. I reckon, it will happen again, Byes' Theorem or no, especially if the profit is private, but the risk public. Because what happens depends on interests, not on good science. Why are we still burning coal and oil?