In April, I finished reading the signal and the noise: why so many predications fail-but some don't by Nate Silver. I bought the book after seeing Nate Silver interviewed on the Jon Stewart Show.
Silver launched to fame when he accurately predicted the presidential winner of 49 of the 50 states and the winners of all 35 Senate races in 2008. Before he focused on elections, Silver developed a sophisticated system for analyzing baseball players' potential and became a skilled poker player.
The book is largely about evaluating predictions in a variety of fields. There are chapters covering forecasting in the areas of economics, politics, baseball, weather, earthquakes, diseases, gambling, chess, poker, the stock market, climate change and terrorists attacks. In all of these areas, Silver examines predictions that have gone bad due to biases, vested interests, and overconfidence. He also shows where and how sophisticated forecasters have gotten it right.
Although I have an Agricultural Economics degree, I was really a math and statistics major in college. I was very interested in the field of econometrics: the branch of economics concerned with the use of mathematical methods in describing economic systems. We used computers to build models of the economy. After taking a couple of graduate level class, I realized that I was more interested in the computers than in econometrics.
One of Silver's comments hit close to home. He notes that "the idea that a statistical model would be able to 'solve' the problem of economic forecasting was somewhat in vogue in the 1970's and 1980's when computers came into wider use." Silver goes on to say that "improved technology did not cover for the lack of theoretical understanding about the economy; it only gave economists faster and more elaborate ways to mistake noise for signal." I graduated from college in 1979, right in the middle of this period. Professionally, I am probably very lucky that I got opportunities to pursue information systems as a vocation rather than econometrics.
The signal and the noise was named by Amazon.com as the #3 best nonfiction book of 2012. While I found some parts of the book very interesting, I struggled through some big sections. I wouldn't rate it as highly as Amazon did. I don't frankly don't recommend it as a general read unless you have some specific interest in forecasting...