One last word about Nate Silver, polling, etc. If someone disagreed with the outcome of Silver’s model or a recent poll, it does not mean they’re opposed to “math” or “science.” I’ve seen that criticism go unchallenged too often, including in the comments here. What was being criticized (incorrectly, as it turns out) was the underlying assumption of what the electorate would look like. This isn’t looking at the entrails of an ox, this is suggesting one key variable in the predictive model was incorrect. In other words, “math.”
Polling is working with smaller and smaller numbers of telephone responses as a percrentage of the calls they are making. There will be a point in the future where the telephone poll is as useless as an internet poll. That’s just basic “math” and the economics of polling. We’re not there yet – clearly – but that day is coming.
As I wrote recently,
Michael Barone, an analyst I greatly admire, said on Fox News election preview program on Sunday that Pew Research were only able to complete 9% of their phone surveys in 2011. The difference of those answering a poll and those not answering a poll is now an independent variable that can potentially affect the outcome of the poll. If the fate of Schrödinger’s cat is dependent upon us making the observation when we open the box, our ability to make the observation is increasingly dependent on whether the cat jumps in the box.
So I was wrong this time to criticize the Marquette Poll as having “St Norbert’s disease” or “off-the-wall wackadoo.” I’ll probably overlearn from this experience, along with so many other pundits, and trust the polls until they’re wrong and we’re embarrassed again.
I just hope Nate Silver’s model doesn’t find the launch codes.