Just came back from voting. Was voter number 2 (dangit, always one guy who makes it there before me).
If you don't know what the title is referring to, check this out. Lots of fun.
I started getting this stuff together on Nov 5, and will fill in the numbers tomorrow morning. I'm having fun listening to Rush pointing out that various Obama campaigners are trying to get out the Dem base. Like, the hardcore base. That's gotta suck to be in that place. Also him making fun of the CNN D + 11 poll. Ha ha ha.
Reminder to my fellow Romneyites: sign up to make phone calls - I will not be able to make calls today, but I'm sure it will be going on all day. It's lots of fun! Sign up! Act! Get more Romney voters to the polls!
Next time I post, it will no longer be a prediction tracker, but checking these predictions against results.
First up, popular vote polling:
Reminder on Unskewed Polls outlier: that's their election day prediction, the other points are poll averages (their "unskewed" poll). I'm keeping the outlier to check against what happens.
RCP: Obama, 48.9%; Romney, 48.2% (increased for both)
Nate Silver: Obama, 50.9%; Romney, 48.3% (a couple of a tenths of percentage points to Obama)
Unskewed polls: Obama, 48.9%; Romney, 50.7% (I'm taking their result prediction for this one, which I will use instead of their earlier outlier)
Electoral College projections:
RCP: Obama, 201; Romney, 191; Toss-up, 146 (no change)
RCP No Tossup: Obama, 303; Romney, 235 (no change)
Nate Silver: Obama, 314.6 Romney, 223.4 (shift of 7 votes to Obama)
Unskewed polls: Obama, 263; Romney, 275 (ok, they changed their ultimate projection – major move down for Romney, lost multiple states)
Win probabilities: (will not necessarily add to 1)
Nate Silver: Obama, 91.6%; Romney 8.4% (big move to Obama…and that's a mighty bold prediction, Mr. Silver)
InTrade: Obama, 68.6%; Romney, 31.0% (3-ish percentage points to Obama….it's going to be moving a lot today, I think)
Final pre-election stories:
From PJ Media columnists, their predictions
Bob Krumm mapped out five possibilities: one, two, three, four, five. Here's his actual prediction.
Aw, Obama couldn't bring out his Madison base in Romney-like numbers.
Say bye-bye to the Obama media
Biden's appeal is becoming more selective
Too close to call! November 3, 1980. Reminder: result was 489 electoral votes to Reagan. With only 50.7% of popular vote. HMMMM
Speaking of 1980, Tapscott thinks that's exactly what we'll get.
Obama plays half-empty arena in Ohio. Obama's appeal is becoming more selective, just like Biden. Not sure if it explains why he cried, though. Come on, Barry, look at it as hall full. Be an optimist.
Early-voting Dixville Notch result.
Kevin DuJan at HillBuzz points out something I didn't know but am totally not surprised by: Dean Baker is a Nate Silver believer. Now, I'm sure you're thinking "Who is Dean Baker? Why do you care?" He is one of my mini-nemeses in the public pension arena (he has no idea I exist, which is fine.) A taste from a prior post:
In my prior post, I had linked to a union-backed piece wherein Dean Baker, he of the dodgy math, said that even when there are some investment losses, the funds have 30 years to make it up.
Really? When you’ve got people, lots of people, drawing benefits right now? Assets will have to be liquidated if the contributions don’t keep up with the outflows. How’s that working out for pensions?
I am not a law-talking type—I am a numbers type, specifically the type of person who projects numbers out under different scenarios. So while it’s a nice, juicy legal puzzle to deal with trying to get current pensions ramped down, I am not overly concerned on the matter inasmuch if and when the money runs out the government cannot proclaim more money to exist (unless you’re the Fed, but that’s not really creating money; I don’t want to get started on that now).
Related to that, here is Sarah Hoyt on the End of Cake - reminder, you can try to vote yourself more free crap, but that free crap will last only so long. Worry not, no matter who the winner is, the pension problem is not going away. There are some interesting things afoot in California and Illinois right now, and I will be getting back to that stuff soon enough.
Blast from the past (summer):
The Wisconsin exit poll evidently reported the race for governor in the recall ballot as 50%-50%. With 92% of the vote in, the Milwaukee Journal Sentinel’s excellent website reports the score as 54%-46% Walker. Let’s say that’s the final results: only 13% of precincts from Milwaukee County and 3% of precincts from Madison’s Dane County—the Democrats’ two reservoirs of big majorities—remain uncounted. It has been emblazoned on mainstream media that the exit poll also showed Barack Obama leading Mitt Romney in the state 51%-45%. But if you think the exit poll was 4% too Democratic—and that’s in line with exit poll discrepancies with actual vote results over the last decade, as documented by the exit poll pioneer, the late Warren Mitofsky*—that result looks more like 49%-47% Romney. Or assume the remaining Milwaukee County precincts whittle Republican Governor Scott Walker’s margin over Democratic Milwaukee Mayor Tom Barrett to 53%-47%, which looks likely, the Obama-Romney numbers would look like 48%-48%.
That was from Michael Barone in June. Just FYI. My ending:
Now, I would love to think that Obama and Romney are neck-and-neck in Wisconsin, but I'm in doubt that the fall electorate will be the same as that for the recall, for a variety of reasons. For one, I bet there's a lot of people in Milwaukee not particularly worked up over Walker, and so didn't bother to vote on Tuesday. Some hundreds of thousands more people voted in the 2008 presidential election than in the 2012 recall. I can think of lots of reasons why said people wouldn't have voted this week (for example, school is out for the summer for college students).
So let's not get cocky, Barone.
By the way, Wisconsin is in play.
Last numbers bit – someone asked me to relook at Nate Silver's "Tipping States" distribution I did. Here is the result for complete independence:
And here are the "extreme" results:
I used the Frechet-Hoeffding upper bounds to develop that. Put simply, I made all the states ultra-depedent on each other. If the least probable state wins for Romney, then they all do. If a state of probability p for Romney goes for him, then all having higher probability also do. That's why there's a weird distribution - there's a clustering of some of these states having very close probabilities, so they tend to go in pairs. Here's my underlying spreadsheet.
Okay, that's it for me today.