The literary equivalent of sex on the beach in the moonlight with your soulmate.by Katie Delahaye Paine
Okay, I’ll admit it, I have a wicked crush on Nate Silver. (And, for all you automated sentiment analysis tools out there, that is a positive statement. I just happen to hail from New Hampshire, where the stuff we love is "wicked good.") Not only is he brilliant and a wonderful writer, he’s made data geeks like me cool.
And yes, I think he’s totally hot. Not in a George Clooney way, but in an adorable, I-want-to-take-him-home-with-me sort of way. Nate, if you read this, I’m not a stalker. But you are on my bucket list of people I’d like to meet before I die.
He first came to our attention back in 2007 when we were analyzing coverage for Michigan State University, where his father teaches. He had just published his first meta analysis of data preceding the 2008 election. A post covering that analysis, and mentioning MSU and his father, quickly grabbed the record for the most number of comments we’d ever seen.
In this most recent election cycle, Nate Silver’s work was the talisman that enabled my fellow progressives in NH to get any sleep at all. We’d meet over coffee or at campaign headquarters and agonize over our fears and the latest polls for hours -- until someone would say, “But Nate Silver says…” I had friends that would check his Five Thirty Eight blog every half hour.
The most interesting aspect of Silver’s book is its exposure of just how flawed most predictions can be. The reason? A limited, or perhaps flawed, view of the world. He makes a strong argument for the Bayesian theory of predictions. Bayesian statistics suggests that all predictions be expressed as a probability of occurrence and that anytime a prediction is tested, the results should be used as a priori evidence for the next prediction.
So, for example, if want to predict the likelihood that a particular action will result in a social media s==t storm, I would take into account all the very latest data on crises and social media responses. Then, once my prediction is either proven or disproven, that result becomes data that goes into the next prediction. It’s actually a lot more complicated than that. But what he is saying is that before you predict anything you need to make sure you look at all the prior predictions and be willing to think differently about the problem you are researching.
Key to his success is the creativity and broad-mindedness with which he considers his variables. Which is why I wish every communications researcher and advisor would read this book. His examples of the things that were not taken into consideration when predicting the housing crisis or the big tsunami of two years ago made my hair stand on end.
In the world of measurement I see clients do it all the time. How many organizations do you know that fail to measure the success of their competitors? Or who test the health of their SEO by googling their own brands, not what the market is talking about? It’s these unknown, or at least unmeasured, factors that will determine the accuracy of your predictions and your research.
For people who do research for a living, or love data and statistics, The Signal and The Noise will resonate, teach, and inspire. It is the literary equivalent of sex on the beach in the moonlight with your soulmate.
For prognosticators, politicians, and consultants, and experts, either read it and mend your ways, or be very, very careful about what you say in the future.
Katie Delahaye Paine is Chairman, KDPaine & Partners, (a Salience Insight company), and Chief Marketing Officer of News Group International. KDP&P delivers custom research to measure brand image, public relationships, and engagement. Katie Paine is a dynamic and experienced speaker on public relations and social media measurement. Click here for the schedule of Katie’s upcoming speaking engagements. Katie and Beth Kanter are authors of the book “Measuring the Networked Nonprofit,” to be published this year by Wiley.
The Measurement Standard is a publication of KDPaine & Partners, a company that delivers custom research to measure brand image, public relationships, and engagement. Katie Paine, Chairman of KDPaine & Partners, will be glad to talk with you about measurement for your organization.