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

    Join 10 other followers

  • November 2014
    S M T W T F S
    « Oct    
     1
    2345678
    9101112131415
    16171819202122
    23242526272829
    30  
  • Recent Bookmarks:

  • Archives

  • Categories

  • Pages

2012 pWP Recap

So… this only took two years to get around to…

My pWP stat is just an easy way to understand and aggregate multiple polls into a single, simple statement: Candidate X is (blank) percent likely to win his or her race. I’ve written a bunch of stuff on pWP, just in case you need to catch up.

A majority of the time, I was only paying attention to the presidential race in 2012. I did not keep up with the various other races. In the presidential race, with its many polls and good data, I went 50-51 in predicting where electoral votes would go (I did not pay attention to Maine or Nebraska’s split-vote system, as there was no need, there were no swing congressional districts in either state). The only state that pWP got wrong was Florida. Which makes sense, Florida was the closest election, with .88% (i.e. less than 1%) difference. However, looking back, had I eliminated an obvious outlier poll, or if I had looked at the median pWP instead of just the mean, I could have gotten closer to the right answer. Bad polls essentially remove the basis of pWP, so finding and eliminating them is a key challenge.

In addition to the presidential race, I made predictions on election night in seven other tight races (6 Senate, 1 Congressional) and I went six for seven. The race I got wrong was the North Dakota Senate race between Berg and Heitkamp. Once again, this was a close race, within 3000 votes. It was the closest Senate race, and relatively poorly polled. There were no polls done in November, and Heitkamp had closed a large gap in the last month of the race. About the only way I could have avoided being wrong in my prediction would have been to not make a prediction at all. Trendlines, using a rolling average, would have projected a 50-50 race. Basically, if there’s little to no current polling, and previous polling shows a tight race, skip the prediction.

The end result of using pWP over the last several election cycles has shown the stat has been a better predictor of the outcome of the race than it should, based on its probabilistic premise. Which means pollsters are doing, at least lately, a better job than even they suggest when giving out their margins of error. I don’t know if this is accidental or purposeful. It could be the way I’m aggregating the polls (when available). I don’t know. But good news is good news.

The bad news is those same polls that were really accurate over the last few election cycles show Dayton and Franken cruising to easy victory. The few partisan polls available in the 7th and 8th Minnesota congressional districts show easy DFL victories as well.

Update: Spoke too early, a non-partisan poll has Mills up on Nolan by almost four standard deviations. That’s over 90% pWP, but I would put it closer to 75% because the strong support for the Green candidate will fall, and the 11% undecided number is too high.

Christie v. Hillary pWP Numbers

So we have our first “big event” of the 2016 election: Christie’s recent “Bridgegate” scandal, and this means we can take a look at how such a scandal affects the political win probability of a candidate.

Before the scandal, a head to head matchup between Christie and Hillary had Hillary up 48-44 with a 4.4 MOE. This gives Hillary an edge in pWP of 65.

After the scandal, Hillary moves up a little, to 50%, while Christie’s support implodes to 37%. New Hillary pWP is 92. So the scandal had an absolute value of 27 pWP (in the wrong direction) for Christie.

Yes, we’re three years out and yes, we’re using a poll that is basically meaningless as far as predictive value for the 2016 election goes. However, it does give us some idea of the seriousness of the scandal and possibly how similar scandals might affect future candidates (or indeed, how much this scandal will hurt Christie as he looks forward at a once promising political career).

From the Notebook

English: Martin Buber in Palestine/Israel עברי...

English: Martin Buber in Palestine/Israel עברית: מרטין בובר בארץ ישראל (Photo credit: Wikipedia)

- The novel is coming along alright. I’m now doing the final edit, and waiting for feedback from my reviewers. I probably won’t be able to release it before Christmas because of my new job. But I’ll try anyway.

- If anyone wants my pWP data for 2012, I made a pdf of my spreadsheets. It’s there if anyone wants to try to replicate my results. Just email me through my About page or leave a comment in this post.

- I am currently working a new job at Walmart, and while it’s not necessary, I do want to say that anything I post here is my own work and views, and nothing here represents Walmart in any way and that I do not represent Walmart in any way, official or not.

- The futility of blogging: In nine years, I have published nearly 5000 posts and earned an invite to the 2008 RNC. In that time, I have earned $11.80 from Amazon.com’s referral program. I’ve “earned” about 17 dollars from Google ads but I can’t collect it. And I got a huge $175 from a one-time text-ad deal. That’s less than 200 dollars. And the sad part is that’s far more money than most bloggers out there will ever earn blogging. The writing bug is just about the worst ill that could befall a human being.

Some pWP notes that didn’t get published during the election, when they would have made more sense:

- Anyone looking really close at some of my pWP graphs will notice the pWP of any individual poll never goes above 95% or below 5%. This is a product of my general philosophy of statistics. There is always some level of “Black Swan-ness” that erodes the confidence I have in the predictability of something like an election. One candidate can die, or commit a crime, or say something awful, etc. These tail events are more common than you’d think, and when combined with the limitations of polling and just a generic fudge-factor, I made the decision that we can never be more than 95% confident a particular candidate will win an election except in extraordinary circumstances. There have been several polls that would have put Obama above the 95% pWP mark, just so you know.

- The tracking polls, which give rolling averages of five or more days, are my nightmare. They basically make my task of trying to calculate the impact of events on the electorate completely impossible. I don’t know how to properly account for them, and they represent a majority of the polls I use for measuring POTUS pWP. I have a few ideas on how to change things for next election, but it basically increases my workload sevenfold.

Reviews:

- How to think about God, by Mortimer Adler. This short book on “philosophic theology” is really incredible. Adler outlines the traditional deductive arguments for the existence of God, and strengthens them. His argument does not require any religious experience, feelings, supernatural experiences or any other questionable claims that are easily discarded by skeptics. His argument, focused on the idea of radical contingency, is surprisingly strong. Anyone interested in theology, and in particular arguments for the existence of God, should read this book.

- Dilbert and the Way of the Weasel, by Scott Adams. This was an abridged audiobook I got for $1.98. And it was good. Adams central thesis is that we area all weasels, and that’s okay. And I agree.

- Finished the Khan Academy Macroeconomics playlist. Conservatives and libertarians generally object to the methods of macroeconomics, and their criticisms are strong. But the vast majority of conservatives and libertarians, at least among those I know, don’t have a strong grasp of macroeconomic orthodoxy. Sal’s playlist gives a very good starting point and puts those criticisms in proper context.

- 2016: Obama’s America. I like Dinish D’Souza. I do. But he destroyed any credibility he had by making this film. imho.

- The Punisher: Kingdome Gone. This was a shortish graphic novel I found lying around the house. It’s older, and a little tame. There’s some kind of underlying political message that I didn’t entirely comprehend about the invasion of Grenada.

- The Walking Dead; Compendium 1. [It’s awesome, just FYI]

- I and Thou, by Martin Buber. I was first introduced to Buber in a Freshman seminar. Since then, I’ve been a big fan.

One Last Little Graph…

Ohio and pWP Graphs

Obama pWP: 52%; Ohio pWP: 73%

Anything in the 40-60 range is a tossup as far as pWP goes, so I can’t predict who will win the popular vote. However, Ohio is strongly leaning in Obama’s direction. Romney has to win Ohio and one other swing state, so I would say there is a one in eight chace Romney wins. Again, this is just based on polling data. I have a gut feeling Romney is going to do better than what the polls are suggesting, but I can’t quantify that.

Here are a bunch of graphs and tables:

Election Day

Updated pWP Table

The Rasmussen and Gallup polls showing Romney up have shifted around the pWP numbers. The popular vote is now a tossup, and Obama’s pWP lead in Ohio has gone down slightly.

Current Obama Ohio pWP: 74%

Hurricane Sandy?

Follow

Get every new post delivered to your Inbox.