• Enter your email address to follow this blog and receive notifications of new posts by email.

    Join 41 other followers

  • June 2018
    S M T W T F S
    « May    
  • Recent Bookmarks:

  • Archives

  • Categories

  • Advertisements

Personal Update

I’ll be taking a bit of a break after the election. My pWP stat did great, it was over 94% accurate in predicting the races where I was keeping track, and that’s a higher percentage than the model itself would expect. The model only failed to be predictive in races where there wasn’t regular polling (North Dakota). I’m hoping to write a long and detailed analysis of the 2012 election and codify all the lessons I learned in using pWP to create a guide for future elections. But I’m going to start a new job here very soon, so I may not get to any of that at all. There will be a few posts on here, from time to time, but for now I have some other big projects to get to. I’m still working on the final draft of a novel, which should keep me plenty busy. Thanks everyone for your interest in my pWP stat, I hope my Republican friends learn to embrace polling as another tool in winning future elections.


Current Obama Ohio pWP: 82%

No graphic, this is just a quick update. A PPP poll was recently posted on RCP; Obama has a 82.3% chance of winning Ohio, based on every publicly available poll released in November. No poll has shown Romney ahead in Ohio since October 28th. Ohio, Michigan, Wisconsin and Pennsylvania have similar enough polling histories (this year) that we can treat the entire region about the same (i.e. they’re not independent of each other, an outcome in one is likely to be indicative of all of them, which is why I haven’t been posting pWP numbers for those other states). It’s practically impossible for Obama to win without Ohio, so I would put Romney’s chances of winning the election right at 20%. In fact, you could probably cut that in half too, as Romney has to win Ohio and one other state, and that state is likely Colorado, where pWP numbers have the race as a coin flip. So let’s call it a ten percent chance Romney wins. Or, every poll done by all the major polling agencies are completely wrong, and Romney will win in a landslide. But I’d start selling those Romney Intrade contracts and buying Obama, if I were you.

Current Obama pWP: 46%

Here’s Obama’s pWP for the last 11 polls taken over the previous week (the data overlaps so you don’t see all the dots), with a linear trendline:

And here’s the table of rolling averages:

I don’t feel comfortable predicting who will win the popular vote, but I would feel especially uncomfortable with the way the race is shaping up if I were Mitt Romney.

Current Obama pWP: 43%

The pWP spread continues to shrink:

And Obama’s moving averages are slowly moving up:

As a general rule, I consider any pWP between 40 and 60 to be a coin flip. And, barring a surprise, it looks like predicting who will win the popular vote in this race will require a fair coin toss, not a collection of polls.

Current Obama pWP: 42%

Obama’s numbers are consistently ticking up, bit by bit:

Also, I’ll be keeping track of all the nationwide polls as they’re posted, and I will be giving two and three-day rolling pWP averages:

I think I’ve approached the limit of my OpenOffice spreadsheet abilities, as I won’t be able to graph the rolling averages they way I’d like to. However, this should be fine, I’ll just have to publish a bar graph every day.

Who’s Ahead?

Polls are being posted everyday, and the data is coming hard and fast. As my previous two posts have suggested, it’s not entirely clear who, between Romney and Obama, is going to win the popular vote. So let’s take a look at the data, first Obama’s:

The numbers are showing quite a bit of spread, but it’s getting better. Over the last week or so, Obama looks to be polling between 45% and 48%.

Here’s Romney’s graph:

As you can see, there is a much greater range when it comes to the GOP nominee. The graph shows a hammerhead-like formation as we enter the final week of the campaign. Pollsters are having a [more] difficult time finding the electorate’s propensity to support Governor Romney. Maybe it’s because of Romney’s chameleonesque political liturgy or just because he’s not the incumbent with four years of apocalypse-free stewardship.

Still, there’s a strong level of support at the 49% mark. If Obama is at the top of his range, the race is 49-48.

In terms of pWP, Obama has 32% chance of winning the popular vote, assuming undecideds break proportionally. But, this is not normally the case. There are a few general rules when it comes to predicting how a race plays out in terms of turnout: 1) Undecideds break away from the incumbent, unless the economy is really rocking; 2) Democrats do better in POTUS election years; 3) The base of the party out of power has a stronger turnout.In this election, the economy question is open, but most people are unhappy with Obama in this category. Point 2) favors the Dems, and point 3) favors the GOP. Things look pretty good for Romney again. Of course, Ohio is where all this really matters. And Obama is still in control in Ohio.

Current Obama pWP: 36%

Regardless of whatever political analysis being floated on the subject, the debates have been a very big net positive for Mitt Romney. He enters the final debate tonight with a slight lead in pWP.

Current Obama pWP: 77%

The preliminary pre-debate pWP numbers are in, and right now Obama has a significant lead of 77% pWP:


There has been a meme spreading among conservative commentators that pollsters are getting their models entirely wrong when it comes to predicting the actual breakdown of voters in the upcoming election. It’s an interesting thesis, and one we can attempt to analyze using pWP as a test.

Any use of statistics must involve some kind of logical framework, a qualitative analysis, or else you’re just data mining (data mining is bad because random patterns will emerge in large data sets purely by chance). So what is our qualitative analysis of the 2012 presidential election? Do we, based on our experiences with past elections and our knowledge of the two candidates, think this election is basically an automatic win for one side or the other?

No, of course not. We know what those races look like. At least, those of us who remember Bob Dole do. We can say with confidence, without using any polls or census data whatsoever, that Keith Ellison will win re-election. The same goes for Nancy Pelosi, the same goes for many matchups that are basically decided long before anyone starts campaigning (excepting tail-events).

The current presidential election is not one of these races, unless you’re a mesmerized partisan. This knowledge in hand, we can look at pWP to help us find those polls that appear to be outliers because they suggest one candidate or another has a substantial lead (probability of winning) far beyond what our qualitative analysis would predict.

In the following graph, I have divided up all the polls taken since Romney picked Paul Ryan as his running mate into five categories based on pWP. Any poll that  has a result of 90% or higher is an outlier. Any poll between 40% and 60% pWP is a tossup, and the rest all lean either Obama or Romney.

As everyone can see, there are a lot more outliers for Obama than Romney. But it should be noted, most of Obama’s outliers are clustered around the convention, and Romney’s outlier also dates to his convention. Still, at least three polls recently have been outliers for Obama, depending on the arbitrary point where decide “positive convention coverage” ended. If we remove the outliers and look just at the polls working within our qualitative framework, Obama is still looking good. If you split the tossup polls, and add the Lean Obama polls, and divide by the total number of polls that aren’t outliers, you get a 67%, let’s call it ‘propensity,’ for Obama to win. And how about that, more pWP convergence.

Obama pWP

I’ll be tracking Obama’s political Win Probability, a neat stat I invented a couple years ago to turn the standard horserace polls into usable and meaningful information, through to election day. Right now, heading into Romney’s primetime convention speech, Obama has a significant pWP lead:

I take my numbers from RealClearPolitics, and calculate pWP based on the methods described in my first pWP post, which I’ve tacked to the frontpage of the blog.