Modesty forbids me, but honesty compels me: my 15-month-old predictions for the 2008 Presidential elections have thus far been so spot-on, it’s spooky. I know that many of you have clamored for us to drop the science stuff from our blog entirely, and just talk about politics and/or our personal lives, topics that are severely under-served in the blogosphere. My own preference would be to focus exclusively on physics, to the exclusion of any other topic of any possible interest, but who am I, anyway? This is a blog, after all, and I think we can all agree that the loudest commenters should have final say on what we post about.
Therefore, I feel compelled to offer up another round of predictions, now that we’ve narrowed the field to two major candidates. By why not make it more fun and have a prediction contest? Anyone can join in, just by leaving your prediction the comments. Entries that appear before the end of June will officially count.
But to make things somewhat science-y, let’s use equations to judge who will win. Each prediction consists of two numbers: the fraction f of the total popular vote cast for the two major candidates that goes to Barack Obama, but also the standard deviation σ of your prediction for that percentage. We are thus ignoring the electoral college entirely, and dealing with the annoyance of third-party candidates by concentrating exclusively on McCain vs. Obama. And we are assuming for purposes of misleadingly-precise quantification that each prediction follows a normal (Gaussian) distribution:
$latex displaystyle P(x) = frac{1}{sigma sqrt{2pi}} expleft(-frac{(x-f)^2}{2sigma^2}right) ,.$
And here is the rub: the winner is not the one whose fraction f is closest to the final answer, but the one whose value of P(x) is the highest, when x is equal to the fraction of votes Obama actually does win. The smaller your standard deviation is, the higher your P(x) will be for x very close to your predicted value f , but the faster it will die off as you get further away. So if you are extremely confident, you can ensure victory by choosing an appropriately tiny standard deviation on your prediction. Contrariwise, if you choose a large standard deviation, you might get lucky if none of the confident folks comes close to the actual result. Cool, eh?
So here we go: I predict that Obama will win 55.5% of the popular vote fraction, with 1.5% standard deviation. That’s right — a blowout. Might be crazily optimistic of me, but right now the portents are good. In Obama’s favor, the current electoral map is extremely favorable (not that it matters for our contest), he is an energetic and charismatic campaigner, his organization is impressively seasoned and effective, he will have twice as much money to spend, Democratic identification among voters is soaring, the incumbent President is world-historically unpopular, various economic crises are putting the squeeze on middle-class voters, the war in Iraq is hugely unpopular, and McCain is a bumbling and unconvincing candidate with a tattered organization, little support among the party faithful, a disturbing penchant for changing his mind and misunderstanding his own policies, and little interest in anything other than foreign policy. In McCain’s favor, Obama is black and his middle name is Hussein; also, McCain has a great rapport with the press, who respect his maverick image. Overall, I think the scales are pretty heavily tilted on this one, and I will not be surprised if McCain replaces Bob Dole as the Presidential candidate that Republicans would most like to pretend never happened.
Of course, I could be wrong. So let’s hear your predictions! The winner will receive a lifetime subscription to Cosmic Variance. Or maybe a T-shirt, if we get caught in a generous mood.
If I wasn’t extremely paranoid about the chances that some silly little gaffe from the Obama campaign will be successfully blown up by the right-wing noise machine into something that swings the election McCain’s way, I would be as optimistic as you are. 🙂
Let’s go for 52% with a 2% standard deviation
I predict Obama will lose with Mccain winning the popular vote and electoral vote. It will not be as close as people thing. mccain will win 52% of the popular vote plus or minus 1%
48% Obama to within 1% – as if the election had been held today and he gets the leaners.
Mccain – qualified, media loves him, experienced, is on track to raise a lot of money, obama is like michael dukakis (who was ahead of the first Bush by 10-15%! 4 months before the election).
no democrat has won the GE without winning west virgina since 1916.
no president has won winning two of the three of ohio, pa and florida since 1960
the demcs are divided big time and more and more dirt comes out on obama everyday. the rnc will destroy him by november.
I predict – that FiveThirtyEight is going to change the face of electoral predictions after this year. His focus on simulating the elections based on poll results, including demographic factors, etc and then calculating the thing people actually care about, the win probability, is refreshingly rigorous compared to what we have seen in the past.
As for the vote share, I’m going to say Obama by 10 (ie 45-55) with a stdev of 1%. No point in staking out largely the same ground as you if I have a lower stdev, is there?
*Especially* after seeing the stark contrast in speeches on Obama primary victory night, I’ll go Obama 54.5%, sigma=0.75%. Get in line behind me, punks!!1!
Obama, 65-35 over McCain, 4% (including elderly McCain’s natural demise). US economic and agricultural collapse by November will test the rule of thumb “nobody votes for an empty stomach.”
54% for Obama, 0.75% s.d.
The meta-strategy here is that the larger the number of bettors, the smaller the optimal sigma. (You could presumably quanitfy this, assuming guesses are also normally distributed.) Of course the farther your point estimate from the average, the larger your signam should be. But I still think Sean’s 1.5% is too large.
The answer can be computed using this model
If we take into account that about 32% of Americans are so conservative that they will always vote for the Republican candidate, no matter how bad he is, then the model describes the 68% of the electorate. Given the current situation, the model pedicts that by election time, these 68% will reach a complete ordered state: they will vote for Obama.
Allowing for some uncertainty about the 32% of, say, 3%, I arrive at my prediction:
My prediction is 68% for Obama with a sigma of 3%.
Sean is correct. I’ve never called an election or NBA Championship incorrectly.
You can just mail the tshirt to me, now.
f = 51.9%
sigma = 0.6%
In the Spring of ’07 I predicted in an email to a friend that the next U.S. President would not be named Giuliani, Clinton, or Obama, but might be named Edwards, Thompson, or McCain. I’m sticking to that prediction, based mainly on historical precedent — election of Obama would really be a huge, huge, change in several ways.
For what it’s worth, I pride myself on not being a knee-jerk anything, and I’m registered to vote as an independent (“Decline to State Party Affiliation” in California election-ese). Too often Congressional Republicans have acted like a wholly-owned subsidiary of Wall Street and big corporations, and don’t seem to give much of a damn about the loss of American manufacturing jobs. And I like Obama’s idea of raising the cap on Social Security (payroll tax) contributions, which would be a popular way of extending the viability of the S.S. Trust Fund.
On the other hand, while Iran isn’t Nazi Germany, and Ahmadinejad isn’t Adolf Hitler, Obama IS a naive fool, and I have no doubt that the Iranian Mullahs are looking forward to his election, so that they can extend their influence in Iraq, and in the region.
The best way to stay out of war (other than not starting one yourself — cf. George W.!) is to scare the hell out of your potential adversaries. In 1961 the Soviet leadership took John Kennedy to be a wuss, due to his failure to back up the Bay of Pigs invasion with American troops, and for other reasons. That judgment of Kennedy led directly to the Soviet leadership’s decision to put medium-range ballistic missiles in Cuba, which they thought they could get away with, triggering the Cuban Missile Crisis.
Bringing that thought up to date with Obama, I’m guessing that Israel will attack Iranian nuclear installations within a few months (or weeks) of Obama’s election, as Israeli leadership will calculate that the Iranians will have no more respect for Obama than I do. What the Iranians will do then is anybody’s guess, but lots of people think Iran will retaliate by attacking Saudi oil production facilities. Or maybe there’ll be a popular revolution in Iran against the theocracy. Of course, Israel may attack Iran even if McCain wins, but he’s got a much better chance of reigning them in than Obama does.
Anyway, to get down to Sean’s challenge (finally!): sorry, I don’t do popular vote. However, I note that if McCain carries Michigan (where he’s leading) and New Hampshire, I think it’ll exactly make up for Ohio, which Bush carried, but where Obama currently leads. However, if Obama manages to carry Colorado, where he’s currently leading, and/or Virginia, then I assume he’ll take it, and deserve it. If Obama also carries Florida, then it WILL be an Obama landslide.
Obama may be favored to win right now but I think ultimately, he will lose. I believe racists are lying to pollsters in these general election polls more so than the primary polls fleshed out.
Obama f = 49.2
sigma = 0.7
I’d like to use a beta distribution for my prediction, with parameters alpha = 7 and beta = 6.
I predict a terrorist attack or military action in Iran shortly before the election, which will swing the election to the republicans.
Oh, Jeez, Dave, Obama has been anything but a naive fool when it comes to talking about the Middle East. What is naive is to think that simply demanding Iran abandon its nuclear ambitions while refusing ever to talk to them is going to work. They have the US over a barrel with it comes to Iraq (Bush’s doing, not theirs) and they know we can’t afford another conflict while Iraq and Afghanistan have us tied up so they’re probably correct if they see US saber rattling as all bluster.
And all Obama’s been saying is exactly what many extremely experience foreign policy people have been saying for years — including Bush’s own defense secretary for goodness sakes. And how did we end North Korea’s nuclear plans, anyway? Through negotiations, that’s how — but not until years of refusing to negotiate with then produced nothing.
Tying Obama to appeasement is dead wrong and, frankly, a not very clever attempt to scare up more votes for McCain. And that’s all it’s been about for Republicans since 9/11. Scare people into voting for them because they’ve got nothing else left to run on. Well, it’s not going to work this time.
I like fee-free bookie shops.
f = 51.5%
sigma = 2%
(I am making room for an upset.)
I’ll go Obama w/ 50.6% of the vote sigma=.5%
“Krum gets the snitch, but Ireland wins the cup.” If that bet is good enough for Fred and George, it’s good enough for me. Now, if only winning the popular vote actually meant getting elected into office, the world would be a very different place…
” . . . he will have twice as much money to spend.”
Not if you count the money that will be spent by unaffiliated organizations and tough campaign they’ll run. And you’re not factoring in votes that might be taken away by Paul’s crowd and Nader — I know not much, but there’s some chance. 52.2/47.8 plus or minus one percent.
Everyone who pontificates without stepping up and making a prediction is a cheese-eating surrender monkey who is afraid of accountability and heartland American values. I’m not saying you’re definitely a terrorist, but the question has to be asked.
And sorry, all distributions must be Gaussian; anything else is too much work for the score-keepers.
Anyone who’s seen The Price is Right knows that the later contestants have a tactical advantage over earlier ones – they have knowledge of previous guesses. One way to overcome this unfairness is to keep competitors in the dark: I’ve made my prediction, but I’m not telling you what it is! Instead, here’s a sha-512 cryptographic hash of my prediction.
039b6f0e5ddb6cea913fde006959bf7bee712c1d9959b0850a1189837619b0c6
423baccc9a92f8e735f89200c17da4489a0c3952a88783df4f04da1e0bb7002d
f = 54.27
sigma = .75
Sean, I basically agree w/ your numbers: Obama 53.8% with a 1% error. Since I got the top mass and discovery date correct 6yrs before the Tevatron discovery & predicted Obama would be the Dem candidate in Jan ’07, let’s see how I do here. Do you want to know the Higgs mass and discovery date too?
Obama 53.2% variance is .15% So between 53.05% and 53.35% to be clear.
e.