Nate Silver Is King, Long Live Nate Silver

My twitter stream is awash in math this morning, cheering Nate Silver’s exceptional forecasting (“Triumph of the Nerds: Nate Silver Wins In Fifty States”, Chris Taylor wrote), and celebrating the victory of math and big data over pompous punditry.  Jeff Greenfield tweeted, “I, for one, welcome our new Algorithmic Overlord.”

At some level, I thrill to the ascendancy of math, and of math nerds – and I write this as a proud former math team captain (and math team T-shirt designer), and as someone whose very best summers as a teenager were spent in math (and writing) camp at Duke University.  It’s also one of the reasons I love Silicon Valley so much – it’s where nerds rule, and where even emerging VCs promote themselves as “Geeks.”

However, before we turn all of life over to algorithms, as some are suggesting, it’s important to place the election prediction in context.

The accomplishment of Silver’s splendid forecasting was to intelligently aggregate existing data, to accurately summarize the current, expressed intentions of the national electorate.  And we’ve learned that careful analysis is far more useful than blustery experts – something Philip Tetlock has been trying to tell us for years.

At the same time, all forecasting challenges are not created equal, and summarizing current public opinion is a much lower bar than predicting events far into the future – and Silver has been clear about this; it’s others who seem to be leaping ahead.

In many (arguably most) domains, and the further out you go, uncertainty likely swamps the ability of either experts or algorithims to make reasonable predictions – as Taleb, and more recently Mauboussin have discussed.

Discrediting expert predictions seems like real progress – but not if we believe the enduring lesson is to replace one group of fortune tellers with another.  We should certainly strive to use big data and careful math whenever we can – but let’s be careful not to fall into the trap of letting down our guard, and trusting all experts who come bearing algorithms.

David Shaywitz is co-founder of the Center for Assessment Technology and Continuous Health (CATCH) in Boston.  He is a strategist at a biopharmaceutical company in South San Francisco. You can follow him at his personal website. This post originally appeared in Forbes.

3 replies »

  1. I’m really loving the theme/design of your website. Do you ever run into any browser compatibility problems? A few of my blog audience have complained about my site not operating correctly in Explorer but looks great in Opera. Do you have any solutions to help fix this issue?

    Stop by my web site: Thelma

  2. I would like to quote one of my favorite philosophers:

    “It’s very difficult to make predictions …. especially about the future”

    Yogi Berra

  3. The top reader pick on Nate’s blog was someone who mentioned that real issue was what we understood as ‘truthiness’. So healthcare spend causes deficit, global warming is figment of imagination and lower taxes create employment.

    Along with statistics Nate also excelled in narrative. He is sort of Dr Gawande of statistics.

    THCB and healthcare would gain enormously from kind of strong analysis that Nate produces. I have seen so much contradictions here. Some say preventive work, some say the don’t. Some vouch for HDHP, but Matt say instinctively that it doesn’t help chronically ill where we spend the most.

Leave a Reply

Your email address will not be published. Required fields are marked *