Data-driven predictions can succeed-and they can fail. It is when we deny our role in the process that the odds of failure rise. Before we demand more of our data, we need to demand more of ourselves.

You don't want to treat any one person as oracular.

Not only does political coverage often lose the signal—it frequently accentuates the noise.

When you get into statistical analysis, you don't really expect to achieve fame. Or to become an Internet meme. Or be parodied by 'The Onion' - or be the subject of a cartoon in 'The New Yorker.' I guess I'm kind of an outlier there.

I prefer more to kind of show people different things than tell them 'oh, here's what you should believe' and, over time, you can build up a rapport with your audience.

Voters' memories will fade some.

When human judgment and big data intersect there are some funny things that happen