By Nate SilverPublished by Allen Lane
"Obama aside, the indubitable hero of the 2012 US presidential election was the statistician and political forecaster Nate Silver," writes Ruth Scurr in The Guardian. His recent political projections proved to be frighteningly accurate and he has even been credited with making analysis cool.
Silver's book, The Signal and the Noise: Why So Many Predictions Fail But Some Don't, is a "lucid explanation of how to think probabilistically". The broad message is that "more modesty and effort would improve the predictive performance of everyone from the TV pundits to the political scientists".
Subscribe to MoneyWeek
Subscribe to MoneyWeek today and get your first six magazine issues absolutely FREE
Sign up to Money Morning
Don't miss the latest investment and personal finances news, market analysis, plus money-saving tips with our free twice-daily newsletter
Don't miss the latest investment and personal finances news, market analysis, plus money-saving tips with our free twice-daily newsletter
The book is an "achievement", agrees Business Insider's Walter Hickey. He especially likes the tone Silver "trusts the reader and doesn't try to preach or condescend". That makes this book "easily the most clear discussion of statistical forecasting for the average person available".
As the Los Angeles Times's Alex Koppelman notes, Silver isn't shy when it comes to taking on big issues, suggesting "the financial crisis might have been alleviated or even avoided if enough people had considered their assumptions more carefully and searched for the ways in which they might be wrong".
However, praise for the book isn't universal. "It's worth noting that, though undoubtedly a smart guy, his statistical polling analysis is not hugely complex or even novel," says Stephen Henderson on the blog Left Foot Forward.
Henderson also warns that his analysis can't be easily transplanted to the UK, given that polls are conducted at the national level, rather than locally (as they are in the US). As the website Political Scrapbook points out, as a result Silver was off the mark in his final forecast for the last British general election.
"The signal of Silver's own thesis tends to get a bit lost in the noise of storytelling," complains Slate's Matthew Yglesias. This "distracts from Silver's core point: there are still an awful lot of ways for predictions to go wrong thanks to bad incentives and bad methods".
He also notes that the book overlooks the fact that the author's mathematical skills aren't the key factor in his success. Instead Silver's "restless and curious mind" is "where real forecasting prowess comes from".
Princeton economist Burton Malkiel also takes issue with some of Silver's economic analysis. "I found myself unconvinced by Mr Silver's view that it should not be all that challenging' to identify financial bubbles." For example, Silver notes that price/earnings ratios were high at the peak of the technology boom, right before the stockmarket crash. But he fails to point out this was also the case at the start of the decade, right before the stockmarket shot up.
So although this is an interesting read, his arguments are weakened by the way he has "ignored all the false positives".
The Signal and the Noise: Why So Many Predictions Fail But Some Don't by Nate Silver is published by Allen Lane (£25).
-
Rightmove: property asking prices hit record highNews Rising demand for top of the ladder home is boosting asking prices, Rightmove research shows. Is now a good time to sell a property?
-
FTSE 100 hits record highs – why is it rising and will we see more gains?Advice UK equities have been described as unloved for a long time but as the FTSE 100 hits new highs, we explain if now is the time to buy British.
