Election 2008 Analysis

Ok, so I finally got around to analyzing my election predictions. Here's a table.

I correctly predicted the outcome of 50 of the 51 states, missing Indiana.

State	EV	Poll	Proj	Win	Δp	Δa	Error
DC	3	0.45			66.82	85.92	19.1
VT	3	1.17			28.13	37.01	8.9
DE	3	3.02			27.92	25.00	-2.9
NY	31	4.38			27.74	26.69	-1.1
MD	10	0.73			25.80	25.44	-0.4
HI	4	0.66			22.64	45.26	22.6
CA	55	6.64			22.60	24.06	1.5
IL	21	4.14			22.15	25.13	3.0
CT	7	1.92			20.16	22.37	2.2
RI	4	0.76			19.83	27.92	8.1
MA	12	4.16			17.77	25.81	8.0
OR	7	9.62			15.74	16.35	0.6
ME	4	5.87			15.52	17.32	1.8
WA	11	7.03			15.36	17.18	1.8
IA	7	9.67			15.28	9.53	-5.8
NJ	15	9.48			14.12	15.57	1.5
MI	17	9.43			13.89	16.47	2.6
WI	10	10.78			13.24	13.90	0.7
MN	10	13.62			9.91	10.24	0.3
NH	4	13.00			9.77	9.61	-0.2
NM	5	7.14			9.49	15.13	5.6
PA	21	27.15			8.06	10.35	2.3
CO	9	14.57			6.42	8.95	2.5
VA	13	21.06			6.06	6.30	0.2
NV	5	13.12			5.79	12.49	6.7
OH	20	28.72			2.89	4.54	1.6
FL	27	29.05			2.03	2.82	0.8
NC	15	27.25			1.04	0.33	-0.7
MO	11	24.40			0.23	-0.13	-0.4
IN	11	16.09			-0.51	1.03	1.5
ND	3	2.67			-2.67	-8.63	-6.0
GA	15	15.07			-3.23	-5.21	-2.0
AZ	10	7.31			-3.61	-8.52	-4.9
MT	3	5.28			-4.29	-2.26	2.0
SC	8	4.60			-8.64	-8.98	-0.3
SD	3	2.88			-9.13	-8.41	0.7
AR	6	3.06			-9.29	-19.85	-10.6
MS	6	3.53			-9.43	-13.17	-3.7
LA	9	2.26			-10.04	-18.63	-8.6
WV	5	6.24			-10.60	-13.12	-2.5
TX	34	2.53			-11.01	-11.77	-0.8
TN	11	2.31			-12.60	-15.07	-2.5
AK	3	5.71			-13.62	-21.54	-7.9
KY	8	8.52			-14.04	-16.23	-2.2
KS	6	4.03			-16.97	-14.96	2.0
NE	5	0.78			-19.05	-14.93	4.1
AL	9	3.42			-23.08	-21.58	1.5
ID	4	0.71			-23.49	-25.43	-1.9
UT	5	1.76			-24.63	-28.18	-3.6
WY	3	3.38			-26.34	-32.24	-5.9
OK	7	4.25			-26.62	-31.29	-4.7

Unless otherwise noted, I am omitting DC and HI from my analysis. These states were not only significant leverage points as indicated by severe values of the Cook's D statistic, but also represented significant outliers based on their studentized residuals. Because of this and the dismal amount of polling in both states, I have omitted them. (This, by the way, is how statisticians say "these data really screwed up my model so I took 'em out.")

I missed statewise margin of victory by {3.1 average, 2.2 median}. I was closest to correctly guessing the outcome in New Hampshire (which is just dumb luck; that state was crazy!). I predicted 54.5-44.7; the outcome was 54.1-44.5, a net error of 0.16 points. I was farthest from correctly guessing the outcome in Arkansas (damn PUMAs!) - I predicted a 9.3 pt McCain victory; he won the state by 19.9 pts, an error of 10.56 points.

The regression model treated me nicely.

The first plot shows my prediction line (red) and where each state actually fell (blue).
The second plot shows my prediction (x-axis) with my prediction error (y-axis).
Highlighting +/- 4.00 was arbitrary.



My regression intercept has a p-value of 0.484, indicating there is absolutely no evidence that my average prediction varied significantly from the average actual outcome.

The model in total has a p-value of 0.000000000000000000000000000000000224, which besides being an awesomely small number, also indicates the probability of beating my model by chance alone.

On the down side, the regression model coefficient of 1.124 had a 95% CI of {1.057, 1.192}. Because 1.000 is not in this interval, this indictates that my model significantly underpredicted the average differential in each state (for either candidate; in other words, I gave Obama too much credit in red states and McCain too much credit in blue states, etc.).

Finally, my model scored an r-square value of 0.960. In other words, if each state's outcome was determined by the results of 100 coin flips, having my model in hand would be analogous to already knowing the outcome of 96 of the flips. Or to use another analogy, it would be like predicting the rankings of teams in baseball standings for a 162-game season while already knowing how the first 156 games turn out.

And just for curiosity's sake, I was joking about being unjustified in removing HI and DC. While it's true I missed them both by large margins (especially HI), it's clear in the picture below why DC (off to the right) is overly influential in determining the line of best fit. (HI is the point at 23, 45).



Had I included the two states, r-squared drops from 0.960 to 0.956 and significance actually decreases (that's good) from 2E-34 to 8E-35.

So that's all I've got. I won't do anything for the Senate, but it looks as though I will be wrong about Coleman winning Minnesota (I can't believe that is still not settled. I don't feel bad about missing it, and to my credit I did predict that it would be the last race decided.)

Finally, I got the absolute percentages for Obama and McCain wrong - I said it would be 53.1-45.9; instead it was 52.9-45.7. But notice that I overshot both numbers (I just took the fact that Kerry and Bush added up to 99.0% and applied the same assumption to Obama and McCain). In terms of share of the 2-party vote, it broke down like this:

Prediction - 53.64 to 46.36
Actual - 53.68 to 46.32

Adding up the two errors, I missed the national vote share by less than one-tenth of one percentage point (0.08%). I'll take it.

The Most Carthatic Thing I've Ever Seen

I probably didn't use the word "cathartic" correctly.

News Flash: Elections 2010 and 2012 possibly still too close to call

Continuing my series on "Hey, the Republicans aren't going to lose forever," I present this WSJ article about the last time the Democrats won over 360 EVs, 58 Senate seats, and 257 House seats.

Two years afterward the Republicans took the Congress for the first time in 50 years.

MN-Sen: What's going on?

So, Intrade contracts on Franken winning the election in Minnesota have held tight between 30 and 35 for about a week and a half now, which is rather remarkably consistent. In the last two hours, however, the price has shot up to very close to 50.

HuffPo has allegations about Coleman corruption all over their front page, but that wouldn't have any bearing on the election. So if anyone's got any idea about anything else that might be making this happen let me know. If it's just reaction to the allegations, well, just one more bit of evidence that political betting markets aren't efficient.

Cynical Politics?

OK, so it's possible I'm just being overly political here, but do you think it stands to reason that Barack Obama appointed Janet Napolitano to DHS as an olive branch to John McCain, as it removes a very large (and really the only) challenger to his Senate seat in 2010?  Just a thought ...

Liberal Media? Perhaps so ...

It makes sense right?  The media should totally follow the story of a guy if he's in Congress, making laws on behalf of his constituents, and ends up clearly guilty of accepting bribes, yet nonetheless manages to stay extremely close in his reelection bid, only to finally be declared the loser of the razor-thin election roughly a month after the fact?  It's totally fair that the media follows that story, right?

Well, the media has not been doing it's job in following around Bill "Cold Hard Cash" Jefferson.  Jefferson, or BCHCJ as I call him for short (not really), was finally defeated in his re-election bid in Louisiana's 2nd district.  To speak to the relevance of his defeat, the Democrat was defeated in this heavily black district by none other than Vietnamese Republican (don't laugh) Anh "Joseph" Cao.

I know the bribery aspects of his story are older, but I have no idea why this guy got almost no coverage when Ted Stevens was all over the news.  I guess Senators have roughly 4.35 times as much power as Representatives (though Stevens got more than 4.35 times as much coverage) and I suppose the whole 60-seat thing really drove the narrative on the Senate election this year.  Either way, even very involved people I know don't know about BCHCJ, so I think the story was underreported.  Either way, he lost, so hurrah to that!

OK, so now the back-patting is legit

Anybody ever heard of this magazine anyway?

(And, for the record, I called MN-Senate for Coleman, a result that is currently trading at 69% on Intrade)

A Little Overzealous

Dear Missouri,

We know you feel bad. You've gotten it right all but twice since 1900, and the second time you got it wrong, it was against our generation's JFK or FDR or Jesus. That's a pretty big screw up, and we know you want to make it up.

This time, however, I think you've gone a little too far. Now, I like Barack Obama. I think he's a cool guy. And St. Louis has a decent tradition of naming stuff after presidents, like Washington University and the terribly-named Jefferson National Expansion Memorial (better known as "The Arch"). But I don't think that already naming streets for Barack Obama, let alone streets that are (1) pivotal in my life and (2) named by some crazies as one of the 10 best streets in America is the answer. I mean, you can't even say he's a better president than George W. Bush. So let's chill on the accolades and let him try governing first.

Sincerely,
Everyone except Chris Matthews

Quick Links

Life is putting a whole bunch of pictures on Google. Some say these pictures are "important" or "historical."

Minnesota recount data. With 98.67% recounted, Franken leads Coleman 1,188,736 to 1,177,465. In my mind this is a lead of 11,271 votes, but since no media outlet is reporting it that way, I must be missing something.

Presidential portrait morph. Exactly what it sounds like.

Eisenhower's Wiki article. Random, I know, but I'm reading it. Did you know his grandson married Nixon's daughter? Because I didn't.

There's lots of cute animals on the internet, but this is the most endearing thing I've ever seen involving pets.

oh GREAT

Chambliss Wins Georgia Senate Runoff

Saxby Chambliss, an incumbent Republican senator, was
re-elected by Georgia voters on Tuesday in a substantial
victory, ending Democratic hopes for a 60-vote majority in
the Senate that would make it difficult for Republicans to
filibuster the Obama administration's legislative agenda.

Election 2008 won't go away

Tomorrow is the long-awaited runoff between spawn of Satan Saxby Chambliss (here's the latest reason to dislike him) and Jim Martin. I'll save the introduction; the Democrats' hope for 60 senators will finally die tomorrow.

And in Minnesota, the same trend continues, wherein every bit of information we get only goes to further show how little information we have. Norm Coleman's lead has expanded ever so slightly, still generally in the 200s. However, he's also been challenging more ballots than Franken, quite possibly (and smartly, though Franken caught on quickly) to fabricate a lead for the news. Coleman's shrewd strategy is to win the first count and the second, and then even if Franken wins the court battle, Coleman can say that the Democratic Secretary of State and State Supreme Court took democracy from the hands of Minnesotans. Intrade contracts have dropped to 25 for Franken, but I'd say this is a pretty 50-50 battle, and there's no way to go any further than 60-40 in either direction.

I said before that I thought Minnesota's would be the closest Senate race, but even I wouldn't have predicted it would be this close.

Quick Back-Pat Update

Source	Obama	McCain	Dem Error	Rep Error	Total Error
Election 2008	52.8	45.9	---	---	---
RCP	52.1	44.5	0.7	1.4	2.1
538	52.3	46.2	0.5	0.3	0.8
Chris	53.1	45.9	0.3	0.0	0.3

Being a Minnesota Electoral Judge

I found this to be a really interesting exercise. When does a vote count?

McCain wins Missouri

(Update: Here's a newer story)

At least one website is saying that McCain's lead in Missouri is now larger than the number of remaining ballots.

The article was posted yesterday and listed McCain ahead by 4355 votes with 3159 remaining.

Currently, the MO SoS page lists McCain ahead by 3602 votes. By subtraction, there are 1458 ballots remaining, though it could be fewer if more ballots have been thrown out.

As much as I would love a recount, I would consider the chances of Obama requesting one to be near zero, even if he wouldn't have to pay for it (not sure if he would or not).

Side notes: Turnout is up 7% from 2.73M in 2004 to 2.93M in 2008. Bush won the Show-Me-State 53.3 to 46.1 in 2004, a margin of 7.20%. McCain has won the state by approximately 49.4 to 49.3, a margin of 0.12%.

Romney cedes 2012?

I guess you NYT people saw this, but Mitt Romney, who idiot pundits liked to say could have carried Michigan because he graduated high school there in 1965, has an article out today in which he says that the automakers should be allowed to fail.

As a politician who currently holds no office and one assumes is still aspiring towards one, why on earth would you say something like that? What if it happens? Thousands of jobs will be lost, even if the greater long-term interest is actually served. You alienate blue-collar workers, who are becoming more important to the Republican party in the new economy (young white-collar workers did mean that Colorado, Virginia, and to a lesser extent North Carolina were actual shifts in the map this year, just as older, less-educated Missouri also shifted to the right). You certainly aren't gaining any votes by making this proclamation. I could go on, but I guess you guys get the point. Right or wrong, I don't see how coming out with this helps you at all. I suppose there's a chance the majority of Americans favor letting them fail (only with some sort of line about how they've been digging their own grave, which I suppose is fair) but they won't be too happy about it if they get what they want and unemployment spikes. It just seems like a no-win statement.

And Begich takes it!!!

Here's a congratulations to Begich, who just took Stevens' Senate seat.

Awesome NYT County Maps

I feel like this has come up here before but in case it hasn't - I can't stop looking at this map. It's like the coolest thing ever.

This is a comparison of the 2008 Obama-McCain margin with the 2004 Kerry-Bush margin by county. So blue counties got bluer (even if they're red counties) and red counties got redder (even if they're blue counties).



Arizona's mildly redder, no surprise there. I'll say this: while my initial reaction was "hey, everybody turned on the Republicans - except the racists in the south," it looks a bit more complicated. First of all, many poor and/or black people have had to move away from southern Louisiana, explaining part of the shift there. Also, Arkansas clearly has a problem, but keep in mind that it is the (original) home state of a former Obama rival (what was her name again?) and so there could quite understandably be some bitterness there. If you count out those two regions, you're left with what is closer to being Appalachia than the South. So when it comes to racism, maybe coal mines are the new cotton fields?

For comparison, here's the 2008 Obama-McCain margin against the 1992 Clinton-Bush margin: (And even more reason not to call 2008 a presidential landslide)

AK-Senate

In case you hadn't heard, 60,000 ballots later Mark Begich now has a slight 814 vote lead over Uncle Ted Stevens in Alaska. There still remain many ballots to be counted, but Intrade contracts have gone up to about 95 for the Dems to take the seat.

That would be 58 on the books, with MN and GA remaining.

Talk about a bad year for Republicans...

Losing the presidency sucks, but it happens fairly regularly for each major party; losing ground in the House and Senate also sucks, but also has precedent and should not be too painful. The losses that hurt the most (in terms of confidence and mood, not political influence) are the ones like this, where a "teenybopper" takes an elected position from your party.

Post-Election Analysis: House Edition

So how did things go in the House? As of right now we have 255 Dems and 174 Republicans with 6 races undecided. I predicted (split the tossups) 258-177, so right now I'm not looking too bad.

Now, I didn't really stake much on the House races because there just wasn't much information available. I did the best I could to put predictions together based on information from Wikipedia, polls, CQ politics, etc. Interestingly, of the races still undecided, all of them were classified as "Safe" or "Strong" as opposed to "Weak" or "Tossup".

I probably could have put together a better graph, but here we can see that I predicted 253 seats to go to Dems. 245 went to Dems, 4 to Reps, and 4 undecideds. I predicted 172 seats to Republicans. 166 went to Reps, 4 went to Dems, and 2 undecideds. Dems won 6 of the 10 tossups.

There are six remaining races. Ethan Berkowitz will gain on Don Young in AK, but unlike the senate race, the Republican here may have too large of a lead to overcome. Bill "Cold Hard Cash" Jefferson is in a tossup in LA-02. LA-04 is also a tossup. CA-04 features a race that was tight all year, while OH-15 and VA-05 are tossups where every single poll was lead by the same candidate, a Democrat and Republican respectively.