Unlikely Voter

I’m back. The last ten days have seen me move cross country and start to settle in to a new home and a new job.

While I was gone, we had some primaries. So it’s high time we took a look at the delegate situation. Of course, since I started writing this post, word has come out that Rick Santorum is exiting the race, so let’s see if that was the right idea. [More]

Since we last looked at the delegate situation, Rick Santorum has won two state primaries, and Mitt Romney picked up a state caucus, a territorial primary, and a territorial caucus.

Santorum showing the ability to win state primaries is good news for him, but he must now convert that ability into delegates, or this race may be effectively over anyway.

When three candidates hang into the Presidential nomination race after Super Tuesday, it becomes time to check whether anyone can get a majority.

Mitt Romney is close. So far he’s not there, but if current trends hold he will be the Republican nominee for President of the United States, and become so on the first ballot.

According to CNN, both Mitt Romney and Rick Santorum are set to win 6 delegates thanks to their close 1-2 finish in the Iowa caucuses. Ron Paul fell to third place. He didn’t win, and he fell further and further behind as the votes were counted last night.

Not one poll projected Ron Paul to drop to third, and PPP stuck to Paul being in first. I said those polls weren’t predictive. They weren’t. I was right.

I went way out on a limb saying Ron Paul does not win the Iowa caucuses, even when he led a bunch of polls. I still say now that Ron Paul will underperform the polls because the turnout model is unrealistic.

Tonight we find out the truth.

Via Jim Geraghty I find that Michele Bachmann is playing fast and loose with the “statistical dead heat” terminology.

It’s bad enough when people pretend that the Margin of Error is a band of uniform probability, and not a bell curve where the extremes are unlikely. But what Bachmann’s email is saying is beyond belief.

Just for kicks, I’ve taken the Real Clear Politics chart of the Republican race and done two things with it. First, I eliminated all candidates but Rick Perry and Herman Cain. Second, I shifted Herman Cain back about 45 days, and up about 5 points.

Red is Cain. Blue is Perry. The shapes of the peaks look pretty similar to me.

I often counsel activists not to worry overly much about sample sizes. They look small, but the math works out because probabilities of independent events multiply, and the sampling of every respondent is an independent, random event.

But as Ed Morrissey points out, NBC’s new poll really is tiny. The MoE is 10.

The poll itself is unimportant: CNN asked adults about the Space Shuttle program. But the news comes on the front page of the CNN/ORC International poll: “The sample includes 856 interviews among landline respondents and 153 interviews among cell phone respondents.”

CNN is adapting to the new challenges in polling. Will they do well?

Last June the big shock in the polling world was when Daily Kos dropped Research 2000 as its pollster, and then convincingly demonstrated that Research 2000’s polls were faked. So it’s not surprising that in a settlement now reached, Research 2000 is paying Daily Kos cash installments, despite admitting no wrongdoing.

It’s not really news, but people who write often on polls in the offseason do need to find things to write about. So that’s why we have the hubbub about a recent CNN/Time poll which did not grapple with the issue of polling cellular phones. Due to federal law, polling cellular phones requires that either phones be manually dialed, or that surveys be manually conducted. Entirely automated systems of calling cellular phones are illegal.

Pollsters that don’t adapt, will fail.

Since Governor Scott Walker and the Wisconsin Senate had a big uproar over unions of government employees, and that uproar has spread to states like Ohio, there’s been a great deal of issue polling on unions and collective bargaining. I tend to ignore all of it, just as I ignore most issue polling. I’ve gotten comments that this is a failure of the site in fact, that I don’t hit these things more.

I have a standard answer for why I tend to ignore issue polling, though: the results are volatile and easily manipulated, either accidentally or intentionally.

We all knew it was coming, and finally it’s here. The Swingometers have been updated. The House Swingometer includes the 2010 results as a new baseline, and the Electoral College Swingometer includes the 2010 Census-based reapportionment.